2015 Annual International Conference on Biologically Inspired Cognitive Architectures

Sixth Annual Meeting of the BICA Society

November 6-8 2015 – Lyon, FRANCE.

Biologically Inspired Cognitive Architectures (BICAs) are computational frameworks for building intelligent agents that are inspired by biological intelligence. These agents serve both as theoretical models (e.g., in cognitive science, neuroscience, economics and social sciences), and as intelligent controllers for autonomous systems (robots, games characters, smart human/machine interfaces, health applications, etc).

Biological intelligent systems (animals, including humans) have many qualities that are often lacking in artificially designed systems; their purpose goes beyond interacting with a closed environment or solving predefined logical problems. At the time when our understanding of natural intelligence is exploding, thanks to modern brain imaging, ethological studies, and the development of cognitive models mapping brain structures with functions, our ability to learn lessons from nature and to build biologically inspired intelligent systems has never been greater. At the same time, the growth in computer science and technology has unleashed enough design creativity and computational power to generate an explosion of applications in multiple domains.

Research in Biologically Inspired Cognitive Architectures contributes to the development of these applications by addressing the numerous questions raised by the problem of replicating natural intelligence – specifically, the complexity of higher cognitive abilities of the human mind – in an artificial system (widely known as the BICA Challenge). These questions are trans-disciplinary in nature and promise to yield multi-directional flow of understanding between all the involved disciplines.

Points of Contact: Amélie Cordier and Olivier Georgeon.

Photos by Jacques Saadé.

Invited speakers


Luc Steels

Luc Steels

ICREA, Institut de Biologia Evolutiva (UPF-CSIC) Barcelona

https://ai.vub.ac.be/members/steels

Self-Regulating Mental Development

It is now generally recognized that human mental development is a long process that leads to the gradual construction of extraordinary complex structures in interaction with the environment, tutors, and other individuals, including peers. Many of these structures can only be acquired when other structures are already in place. For example, fine-grained grasping with the fingers is only possible when rudimentary control of arm movements has been established. A central challenge for emulating development on (robotic) agents is to orchestrate the ordering in which skills and competences are acquired. There are several methods. For example, tutors can carefully scaffold the complexity of the environment for learning and then gradually increase the challenge. Here we investigate mechanisms in which learners themselves regulate the complexity of the challenges they tackle in harmony with skills they already acquired. I look in particular at mechanisms inspired by Csikszentmihalyi’s flow theory and focus on how this theory suggests way to orchestrate autonomous language learning.


Kevin O’Regan

How a naïve agent can construct the notion of space

As noted by Poincaré, Helmholz and Nicod, the only way our brains can know about the existence, dimensionality, and structure of physical space is by sampling the effects of our actions on our senses. In this talk we show how a simple algorithm based on coincidence detection will naturally extract the notion of space. It can do this without any a priori knowledge about how the brain is connected to the sensors or body, and for arbitrary sensors and effectors. Such a mechanism may be the method by which animals’ brains construct spatial notions during development, or it may have evolved over evolutionary time to allow animals to act in the world. The algorithm has applications for self-repairing robotics and sensor calibration in unknown hostile environments.


Pierre-Yves Oudeyer

Pierre Yves Oudeyer

Research Director at Inria, and head of the Inria/Ensta-ParisTech FLOWERS team (France) (more).

http://www.pyoudeyer.com/

Developmental robotics and open-ended learning

A great mystery is how human infants develop: how they progressively discover their bodies, how they learn to interact with objects and social peers, and accumulate new skills all over their lives. Constructing robots, and building mechanisms that model such developmental processes, is key to advance our understanding of human development, in constant dialog with human and living sciences.

I will present examples of robotics models of curiosity-driven learning and exploration, and show how developmental trajectories can self-organize, starting from discovery of the body, then object affordances, then vocal babbling and vocal interactions with others. In particular, I will show that the onset of language spontaneously forms out of such sensorimotor development. I will also explain how such developmental learning mechanisms can be highly efficient for robot learning of motor skills in high-dimensions, such as learning omnidirectional legged locomotion or object manipulation.


Peter Gärdenfors

Peter Gärdenfors

Lund University Cognitive Science.

http://www.lucs.lu.se/Peter.Gardenfors

The role of attention in human-robot-communication

In research on human communication and child development, the role of attention has become central. In the lecture, I will present some of this research and discuss its implications for how to develop human-robot communication that is as natural as possible. I focus on two questions: (1) How can a robot use the attention of a human to understand what the human wants to communicate? (2) How can a robot control the attention of a human in its communication? For the first question, following human gaze or pointing is required and joint attention should be achieved. The results will be improved if the robot has a model of the interests or goals of the human. For the second question, there are three main methods: speaking, looking and pointing. I will present some results from an ongoing project involving linguistic communication between an iCub and a human and show the importance of attention in the process. Finally, I will present some experiments concerning how humans interpret robot pointing, something which turns out to be quite dependent on the bodily configuration of the robot.


Dori Derdikman

Dori Derdikman

Department of Neuroscience, Rappaport Faculty of Medicine and Research Institute, Technion – Israel Institute of Technology, Haifa.

http://derdiklab.technion.ac.il/

Deciphering the brain’s navigation system

Recently there have been major leaps in the scientific understanding of the brain’s internal navigation system. Several related cell types have been discovered in the brain: Place cells, grid cells, head-direction cells and border cells. These cells are believed to be part of a cognitive map responsible for representation of the brain’s internal sense of space. This brain system exemplifies one of the rare cases in which the internal algorithm of a mammalian neural network could be deciphered. While the phenomenology of these cells is now quite well understood, many questions remain: How are these cells connected into a network? How are they generated? How could they be read out? In this lecture I will describe these major questions and suggest some avenues connecting between the theory of these cells and the growing bulk of experimental evidence about them.

David Aha

Goal Reasoning for Autonomous Control

Goal reasoning actors are highly autonomous; they can decide for themselves what goals to pursue. This requires substantial interpretation about the actor’s recent observations. In this talk, I will describe recent work on behavior recognition, plan recognition, and explanation generation in support of goal deliberation, along with applications of goal reasoning that our group is pursuing concerning the control of autonomous unmanned vehicles.


Piotr (Peter) Boltuc

Peter Boltuc

Piotr Boltuc, The Louise Hartman Schewe and Karl Schewe Professor of Liberal Arts and Sciences, professor of philosophy, University of Illinois Springfield (more).

Introducing BICA Philosophy: (A) No Direct Ontological Access – The Feature we Share (B) The Engineering Thesis of Non-Reductive Consciousness

BICA philosophy is the idea that there is nothing in human and animal cognitive architectures that cannot be instantiated (not just merely replicated, whatever the difference) in a sufficiently advanced biologically inspired cognitive architecture. This radical claim may follow from the physical interpretation of the Church-Turing thesis. Here are two examples of philosophical problems in BICA:

A. All cognitive architectures have merely an indirect ontological access to empirical reality but levels of such access differ. This is true of biological, biologically inspired architectures as well as AI. Systems that are purely reactive are empirically the closest to ontology. The more complex mind-maps a system creates, the further from direct interactions with reality it becomes. This is the problem of empirical access. This problem is well known in human epistemology but it is even clearer in robotics.

Olivier Georgeon, in his recent work, points out to the opposite problem. If we use a cognitive architecture “to solve problems that we model a priori (e.g., playing chess etc). Then the model of the problem constitutes a reality as such and the cognitive architecture receives a representation of the current state of the problem as input data. In this case, the architecture has access to its noumenal reality (the problem space).” I would call it the Platonic scale of ontological access where mathematical equations are identical with reality but the problem is their fit as a model of the empirical world they are supposed to describe and predict, an old problem in philosophy of science.

B. If we come to understand how a human brain operates, we should also know how it operates first-person stream of consciousness. To understand anything at a BICA level is to be able to reverse engineer it. Hence, we should be able to reverse engineer first person consciousness.

This claim has philosophical as well as engineering implications. Most people today think that computation of complex data is the gist of first person consciousness; this is in part because they view first-person stream of consciousness as spooky (a dualistic remnant of religious notions of the soul). But a simpler hypothesis is that the stream of consciousness is more like hardware (a stream of light generated by a light bulb or a reflection generated by a mirror); nothing spooky about those. Information is just the content engrafted in such stream. Hence, to preserve one’s conscious self is to preserve the stream – to preserve the content of such stream is to preserve information about it.


Massimo Cossentino

Massimo Cossentino

National Research Council of Italy. http://www.pa.icar.cnr.it/cossentino/ .

Holons and System Adaptation

Holons are the basis for building very scalable yet simple architectures. They spring from the observation made by Koestler that the concepts of ‘whole’ and ‘part’ have no absolute meaning in the reality. A whole or a part can be easily identified in many contexts but at the same time they can be seen as opposite. This philosophical concept has a perfect correspondence with software architecture. Nowadays, it is very diffused to approach complex systems as systems of systems. They can be seen as intrinsically recursive when considering that each of the composing systems may be decomposed into its components that in turn may be individually addressed or regarded as an assembly of (sub-) systems/components/classes. Each of the parts at whatever level of abstraction has the dignity of a complete entity (a whole) but at the same time it may be further exploded at finer level of details (as parts). Holons offer a great way for representing complex systems and solving several real-world problems but their recursive, dynamic nature may be a challenge at design time. In this talk, holons will be the common denominator of a path that discusses the design of holonic systems and their great contribution in achieving runtime system-level adaptation of cognitive multi-agent systems, for instance during the execution of norm-constrained workflows. The presented contribution of holons towards system adaptation lies in the hierarchical self-similar structure of the holonic architecture. They allow the decomposition and representation of intentional systems that achieve effective goal-oriented solutions, at the same time they become a proficient structure to be learnt for future reuse.


Frank Ritter

Applied Cognitive Science Lab. College of IST. Penn State University. http://www.frankritter.com/.

The need for high level compilers for generating low level behaviors

There is a need for high level languages to help create low level BICA behaviour. I’ll present an example compiler for creating ACT-R models from hierarchical task analyses for a non-iterative, 30 min. task, where we created models of 11 levels of expertise in an afternoon. The models start with about 600 rules each, and learn out to 100 trials about another 600 rules. We compared these models to human data over four trials (N=30) and both the aggregate and individual data fit the novice best (or nearly best). This work shows that high level compilers can help manage the complexity of large models. I’ll then note some future work including microgenetic analysis and modeling of learning curves on the individual subtasks and also look at forgetting of these tasks after delays ranging from 6 to 18 days.

Program

Conference Booklet.

Friday November 6th will welcome two collocated events in parallel with BICA:

  • Morning: Technology demo/Industry meeting. We are inviting local industries and startups interested in robotics, artificial intelligence, and cognitive science. They will showcase technology demos in parallel with some BICA participants, including Alain Mille, Peter Dominey, Sherine Antoun, Mark Waser, Ignazio Infantino. This meeting is intended to favor exchanges between academic research and industry.
  • Afternoon: Symposium on Biomimetic approaches for sustainable development. Invited speakers: Jean-Louis Deneubourg, Yves Duthen, Nour-Eddin El Faouzi. We encourage bidirectional communication with BICA.

Below is the BICA program. Abstracts are available in the Easychair smart program.

BICA 2015 Program Plenary sessions Concurrent sessions Poster session
Program numbers are given on the left of each name *Asterisks show session chairs
Day 1: Friday November 6
8:00 am – 8:30 am: Registration
8:30 am – 10 am: Concurrent CS1 CS2 Reservoir computing
08:30 106 Alexei Samsonovich* 95 Jure Zabkar* 79 Peter Dominey*
09:00 64 Tarek Besold 47 Mark Waser 71 Bruno Golosio
09:30 19 Daqi Dong 63 John Tsotsos 80 Joni Dambre
10:00 am – 10:30 am: Coffee
10:30 am -12:00 pm: Concurrent CS3 CS4 Reservoir computing
10:30 81 Paul Robertson* 100 Paul Verschure* 96 Pierre Enel
11:00 60 Dane Corneil 101 Frank Ritter 33 Grégoire Pointeau
11:30 43 Junya Morita 75 Douglas Summers-Stay Panel
12:00 pm – 1:30 pm: Lunch
1:30 pm – 3:30 pm : Plenary Plenary 1 (Peter Dominey*)
01:30 94 Wolf Singer
02:00 105 Dori Derdikman
02:30 104 Kevin O’Regan
03:00 31 Peter Boltuc
3:30 pm – 4:00 pm: Coffee
4:00 pm – 6:00 pm: Symposia Computational Narrative Enaction Developmental learning
04:00 90 Mark Finlayson* 99 Pierre De Loor* 3 Olivier Georgeon*
04:30 73 Nicolas Szilas 5 Leonardo Lana de Carvalho 93 Alain Mille
05:00 57 Carlos León 37 Ricardo Gudwin 4 Rémi Casado
05:30 Panel 22 Muneo Kitajima 69 Simon Gay
7:30pm – 8:30+ pm: Reception
Day 2: Saturday, November 7
7:30 am – 8:00 am: Registration
8:00 am – 9:30 am: Plenary Plenary 2 (Alain Mille*)
08:00 a) Luc Steels
08:30 85 Peter Gardenfors
09:00 58 Matej Hoffman
9:30 am – 10:00 am: Coffee
10:00 am – 12:00 am: Plenary Plenary 3 (Tarek Besold*)
10:00 b) Pierre-Yves Oudeyer
10:30 27 Don Perlis
11:00 25 Owen Holland
11:30 9 Koichi Takahashi
12:00 pm – 1:30 pm: Lunch
1:30 pm – 3 pm: Concurrent Consciousness Architecture Creativity
01:30 7 Junichi Takeno* 21 Muneo Kitajima* 14 Agnese Augello*
01:52 72 Evgenii Vityaev 18 Denis Kleyko 13 Ignazio Infantino
02:14 34 Pentti Haikonen 65 Dilhan Thilakrarthne 51 Atsushi Nomura
02:36 35 André Paraense 6 Falntina Alata Panel
3:00pm – 3:30 pm: Coffee
3:30 mp – 5:00 pm: Concurrent Spatial cognition Social interaction Knowledge representation
03:30 52 Amitabha Mukerjee* 53 Christopher Dancy* 40 Antonio Lieto*
03:52 8 Denis Kleyko 49 Denis Ivanov 10 Hanwen Xu
04:14 11 Haruki Ebisawa 50 Takashi Omori 15 Jean-Charles Bornard
04:36 12 Norifumi Watanabe 46 Albert Fonda 66 Tatt Wee Oong
05:00 pm – 5:15 pm: Pause
05:15 pm – 6:30 pm Announces (103 Alexei Samsonovich*)
05:15 Poster pitches
05:25 BICA Society panel
WBAI Workshop (Tarek Besold*) Poster Session
05:40 Hiroshi Yamakawa
8:00 pm – 11:00 pm: Gala dinner
Day 3: Sunday, November 8
7:30 am – 8:00 am: Registration
8:00 am – 9:30 am: Plenary Plenary 4 (Olivier Georgeon*)
08:00 c) David Aha
08:30 28 Igor Aleksander
09:00 102 Rodrigo Ventura
9:30 am – 10:00 am: Coffee
10:00 am – 12:00 am: Plenary Plenary 5
10:00 84 Patrick Shafto
10:30 16 Ricardo Gudwin
11:00 30 Peter Dominey
11:30 45 Massimo Cossentino
12:00 pm – 1:30 pm: Lunch
1:30 pm – 3 pm: Concurrent Sensorimotor Learning Emotions Neural Networks
01:30 39 Jacques Penders* 24 Max Talanov* 17 Andras Lorincz*
01:52 1 Daqi Dong 61 Mukta Galawat 55 Christian Huyck
02:14 38 Kota Itoda 70 Adnan Manzoor 32 Yasuo Kinouchi
02:36 88 Erwan Renaudo 62 Muh Anshar 76 Sherine Antoun
3:00pm – 3:30 pm: Coffee
3:30 pm – 4:00 pm: Plenary Plenary 6
03:30 Closing discussion

 

program.txt · Last modified: 2015/11/04 11:30 by ogeorge

Post-conference records

Proceedings

Videos

Videos of plenary presentations

Robodanza show

Slides of presentations

André Paraense

Olivier Georgeon

Selected photos

By Allen King

By Simon Gay

By Amélie Cordier

Call for paper

The Call for Paper can be downloaded here.

Scope

With the scope of BICA 2015 covering all areas of BICA research listed below, this year’s major thrust will be on learning from experience of sensorimotor interaction. Here, the key questions are:

  • Learning: how a system that has no direct ontological access to reality can construct knowledge about reality based on regularities of interaction?
  • Self-motivation: what key motivational drives (e.g., emotions, behavioral preferences, social interactions) should we incorporate in models of self-motivated cognitive systems?
  • Methodology: how to assess active open-ended learning? What methods can we draw from biology to define and assess intelligent behaviors beyond pre-defined tasks and pre-modeled problems?
  • Models of interaction with the environment: can we define models alternative to the traditional perception-cognition-action cycle?
  • What emergent mathematical foundations can support sensorimotor and other forms of learning?

In addition to these focus topic areas of BICA 2015, we encourage submission of papers in all areas relevant to BICA research, especially in the following areas:

Neuroscience:

  • “B” in BICA: useful biological constraints for cognitive architectures
  • Bridging the gap between artificial and natural information processing
  • Cognitive and learning mechanisms informed by neuroscience
  • Neural correlates of cognitive and meta-cognitive processes
  • Robustness, scalability and adaptability in neuromorphic systems
  • Neurophysiological underpinnings of reinforcement learning
  • Physiological mechanisms of memory formation and (re)consolidation
  • Representation of contextual and conceptual knowledge in neural systems

Social, Economic and Educational Sciences:

  • Mixed-initiative systems based on inspirations from biology
  • Agents possessing human-level social, narrative, and emotional intelligence
  • BICA in pedagogical, learning, and tutoring technologies and education
  • BICA models of self and their application to self-aware perception and action
  • Representation, perception, understanding, processing and expression of emotions
  • Virtual characters and narratives, artificial personalities and human-compatibility of BICA
  • Agent-based modeling of intelligent social phenomena (are there any?)
  • Applications of BICA technologies in elderly care

Cognitive Science:

  • Perception, reasoning, decision making and action in BICA
  • Combining natural and artificial approaches to cognition
  • Comparison of different forms of learning, memory, and cognitive growth
  • Theory-of-Mind, episodic and autobiographical memory in cognitive systems
  • Introspection, metacognitive reasoning and self-awareness in BICA
  • Models of learning and memory: robustness, flexibility, transferability
  • Natural and body language and its role in intelligence, cognition and interaction
  • Unifying frameworks and constraints for cognitive architectures: the grand unification

Artificial Intelligence:

  • Creativity, goal reasoning and human-level autonomy in artifacts
  • Embodied vs. ambient intelligence: embedding or embodiment?
  • Natural Language capabilities and social competence of BICA
  • Learning by reading, by observation, by reasoning and by analogy
  • Robust and scalable machine learning mechanisms in BICA
  • Self-regulated learning, bootstrapped and meta-learning and the critical mass
  • The place for BICA in tomorrow’s textbook of artificial intelligence

General:

  • Mathematical basis for BICA and fundamental theoretical questions in BICA research
  • Alternative substrates for implementation of BICA: smart materials, quantum and biocomputing
  • Alternative approaches to the development of BICA: evolutionary, system-theoretic, educational
  • Fundamental academic, practical and theoretical questions in BICA research and technology
  • Cognitive Decathlon and Grand Challenges for BICA as components of the BICA Challenge
  • Critical mass for a universal human-level learner and a roadmap to solving the BICA Challenge
  • Metrics, tests, proximity measures and the roadmap to human-level / human-compatible AI
  • Leveraging the cloud, world-wide-web, and social-media: possible role for BICA?
  • Cybersecurity and secure authentication methods based on BICA
  • Interdisciplinary research opportunities involving BICA
  • International trends and opportunities in funding BICA related research

Submission

Please follow the submission procedure on the Submission Page.

Deadlines

Please check the deadlines on the Deadline page.

BICA 2015 Submissions

The following applies to all submissions (the main conference and other sub-events). After carefully reading the instructions, please click on the EasyChair submission link in the Making Submissions section.

Publication Venues

All the BICA 2015 papers and abstracts will be included in the electronic volume of proceedings distributed to the conference participants (this volume will not constitute a separate publication). Additionally, each article will be published in one of the two official BICA 2015 venues:

  1. A special volume of Elsevier’s Procedia Computer Science, indexed by Web of Science CPI and Scopus, just to name a few.
  2. The BICA Journal – an Elsevier journal indexed in Web of Science and Scopus, scheduled to acquire a JCR Impact Factor at the beginning of 2016.

Submission Categories

In accordance with the publication venues, you will be invited to choose from amongst the following categories of submission:

  1. Papers for the special volume of Procedia Computer Science:
    • 6 page research or position paper, including an approximately 150 word abstract. The minimal length is 4 pages. Every additional page should be covered by a fee of 50 EURO at the time of registration. This fee is set to discourage additional pages while not strictly enforcing this limit.
  2. Papers for the BICA Journal:
    • Letters (brief communications of new findings): 3,000 to 6,000 words.
    • Full Research Articles: approximately 8,000 to 12,000 words. Reviews or vision papers may be submitted by invitation only.
  3. Abstracts considered unpublished. Distributed in the electronic volume of proceedings.
    • Stand-alone abstracts: up to 500 words, with the first 150 words constituting a self-contained abstract for the Program brochure.
    • 2-page extended abstract: formatted as a Procedia paper with a 150 word abstract.

Preparation of Submissions

All papers must be prepared based on Procedia templates (Word or Latex):

Please follow the Procedia Computer Science Guide for Authours:

None of the initial submission is required to be camera-ready. However, all final paper submissions must be in a camera-ready form prepared based on the provided Procedia templates and must conform to the Procedia Computer Science Guide for Authors. This is necessary for the production of the combined electronic volume of BICA 2015 proceeding.

The publication venue for each accepted paper will be determined by the Program Committee based on the paper quality, Authors’ preference and Reviewers’ recommendations. All submissions should be prepared based on Procedia templates.

Concerning papers accepted for the BICA Journal: after acceptance and registration payment, authors will be asked to reformat their references in the APA style and upload all figures as separate, high-resolution vector-graphic files, in compliance with the BICA Journal Guide for Authors (this is not required at the time of initial submission). Elsevier will take your Procedia-style submission and manually typeset it for publication in the BICA journal.

For stand-alone abstracts, complementary materials (e.g., a short bio) can be uploaded to help reviewers but will not be included in the conference program brochure.

Making Submissions

To submit your paper, please follow this link; you will have to login to EasyChair as an author, and submit your paper to the BICA 2015 Track:

All inquiries should be emailed to Olivier Georgeon and/or to Alexei Samsonovich.

Processing

All submissions will undergo one round of peer-reviews. The category may be changed based on reviews (e.g., a submission to the BICA journal may be redirected to Procedia). Then, Authors of accepted submissions will be required to submit their final version.

Presentation Venue

All accepted work must be presented at the conference in Lyon (FRANCE). At least one registered participation is required for each accepted paper. To ensure participation of presenting authors, the registration fee payment (plus extra page fees, if any) will be required at the time of the final submission of accepted materials.

Presentations without Submissions

Invited speakers are encouraged, but not required, to submit papers or abstracts. Other participants can have presentations accepted based on an abstract only, without a paper submission.

Registration

  • Early bird registration: 650 euro (deadlines). Late registration: 750 euro.
  • Gala dinner: 40 euro. Panoramic boat dinner on the Rhône and Saône rivers (socials).
  • Extra page fee: 50 euro per page.

Registration fee includes lunches, coffee breaks, and the cocktail party with Robodanza show (socials).

A 50 euro discount is offered to the BICA Society members who already payed their 2015 subscription to the BICA Society. Please email Laure Corriga for the discounted registration procedure.

Registered participants may be freely accompanied by a “plus one” at the cocktail party/Robodanza show.

Registered participants may buy extra gala-dinner tickets for family or friends. On the second page (2/4) of the registration website, check the “Gala dinner” radio button. A numerical field will appear on the right. Enter your total desired number of gala dinner tickets (including you).

To register to BICA 2015, please click here:

For any question regarding the registration process, please contact Laure Corriga.

Important dates and deadlines

Deadlines are Anywhere on Earth (midnight, GMT-12).

  • Paper review feedback and notification of acceptance (first round) – July 20th.
  • Deadline for initial paper submission – August 25th.
  • Paper review feedback and notification of acceptance (second round) – September 10th.
  • Final paper due for BICA Journal – September 19th.
  • Final paper due for Procedia Computer Science – September 30th.
  • Early-bird registration deadline – October 30th.
  • Conference – November 6-8.

Organization

General Program Chairs

Conference Chair

Core program committee

Organization Committee

Program Committee

David Aha, Kenji Araki, Frederic Armetta, Joscha Bach, Tatiana Baidyk, Paul Baxter, Thierry Bellet, Paul Benjamin, Florian Bernard, Tarek Besold, Jordi Bieger, Perrin Bignoli, Romain Billot, Douglas Blank, Jean-Charles Bornard, Mikhail Burtsev, Erik Cambria, Raja Chatila, Suhas Chelian, Olga Chernavskaya, Christopher Dancy, Veronique Deslandres, Haris Dindo, Peter Dominey, Stéphane Doncieux, Jim Eilbert, Thomas Eskridge, Usef Faghihi, Michele Ferrante, Jeremie Fix, Stanley Franklin, Herve Frezza-Buet, Salvatore Gaglio, Philippe Gaussier, Simon Gay, Ashok Goel, Salima Hassas, Ian Horswill, Eva Hudlicka, Christian Huyck, Ignazio Infantino, Eduardo Izquierdo, Alex James, Magnus Johnsson, Darsana Josyula, Yakov Kazanovich, William Kennedy, Mehdi Khamassi, Deepak Khosla, Giuseppe La Tona, Luis Lamb, Leonardo Lana de Carvalho, Othalia Larue, Christian Lebiere, Mathieu Lefort, Jürgen Leitner, Simon Levy, Jinhai Li, Antonio Lieto, James Marshall, Laetitia Matignon, Alain Mille, Steve Morphet, amitabha Mukerjee, Valentin Nepomnyashchikh, David Noelle, Andrea Omicini, David Peebles, Giovanni Pilato, Michal Ptaszynski, Subramanian Ramamoorthy , Uma Ramamurthy, Thomas Recchia, Vladimir Redko, James Reggia, Frank Ritter, Brandon Rohrer, Paul Rosenbloom, Christopher Rouff, Alexander Ratushnyak, Rafal Rzepka, Swathikiran S, Ilias Sakellariou, Fredrik Sandin, Ricardo Sanz, Michael Schader, Michael Schoelles, Valeria Seidita, Ignacio Serrano, Javier Snaider, Donald Sofge, Rosario Sorbello, Terry Stewart, Sherin Sugathan, Junichi Takeno, Knud Thomsen, Guglielmo Trentin, Yury Tsoy, Rodrigo Ventura, Evgenii Vityaev, Pei Wang, Tom Ziemke.

Conference venue

The conference venue is the Novotel Gerland Conference Center. It is located by the beautiful Rhône riverbanks across from the Musée des Confluences – Lyon’s emblematic museum of natural history and societies.

Directions

The Novotel Gerland is close to the “Halle Tony Garnier” station of tramway line T1, and to the “Debourg” station of metro line B.


Local area map: Novotel Gerland BICA2015 venue (BICA icon), Musée des Confluences, “Halle Tony Garnier” tram station, and “Debourg” metro station.

Lyon public transport website: http://www.tcl.fr/.
Saint Exupery airport tramway shuttle website: https://www.rhonexpress.fr/.


Lyon public transport map

Direction from Saint Exupery Airport

  • Take the tramway to Lyon called “Rhoneexpress”.
    • Walk to the Rhoneexpress terminal situated in the train station of the airport.
    • Purchase your Rhoneexpress ticket at the vending machine situated in the train station hall.
    • The ticket inspector will punch your ticket inside the tram. She can also sell you a ticket with one euro extra charge.
  • Get off the Rhoneexpress at its terminus called “Gare Part-Dieu”.
  • Take Tramway T1 towards “Debourg”.
    • Walk to station “Gare Part-Dieu Vivier-Merle” situated on the other side of the Part-Dieu train station.
    • Purchase your tram ticket at the vending machine on the T1 platform.
    • Punch your ticket at the punch machine inside the T1.
  • Get off the T1 at station “Halle Tony Garnier”. The Novotel Gerland is next to the station.

There are fastest routes using Metro A from “Vauls-en-Velin – La Soie” to “Perrache” and then connecting to T1, or using Metro B from “Gare Part-Dieu” to “Debourg” and then connecting to T1 backwards, but you have one more connection and the tram route is more touristic than the metro.

Hotel reservation

Novotel Gerland offers special price to BICA2015 attendees (refundable) from Thursday 5 to Sunday 8. Please follow this link: Novotel room reservation for BICA2015.

Novotel Gerland information:

Other Hotels recommended by the tourist office of Lyon:

Welcome cocktail party and Robodanza show

Friday November 6th, 7:30pm-8:30pm and later.

Lyon tourism office, Place Bellecour, Lyon historic center.

Welcome cocktail party featuring the Robodanza show – a science/art collaboration between the High Perfomance Computing and Networking (ICAR) at the National Research Concil (CNR – Italy), the University of Palermo, and the ARCI Tavolatonda troupe staring Giulia Demma and Chiara Castello.


Robodanza, Place Bellecour, and Tourism Office. Photos by ARCI Tavolatonda and Jacques Saadé.

Gala dinner on the Hermes boat

Saturday November 7th, 8:00pm-11:00pm.

Boarding: 16 Quai Claude Bernard, Lyon (Tram T1 station “Quai Claude Bernard”).

Disembarkment: Novotel Pier

Gala dinner on the Hermes in a 3-hour magnificent city tour on the Rhône and Saône rivers.


The Hermes. Photos by Lyon City Boat.

About Lyon

With its historic center registered to the UNESCO world’s heritage, Lyon is a delightful place for work and pleasure. France’s second city stands at a central point, just two hours of high-speed train south of Paris, two hours driving west of the Alps, and three hours driving north of the French Riviera (Côte d’Azur).

Lyon offers an exceptional quality of life, “art de vivre”, with many pedestrian streets and beautiful walkways on the Rhone and Saone riverbanks. It has efficient public transports and a pioneering public bicycle system.

Lyon is also a city of culture. It organizes many international events, ranging from a renowned music festival in the gallo-roman amphitheater to the “Lumière brothers” international film festival. You will also love the city’s many museums: the new Musée des ConfluencesMuseum of Modern ArtMuseum of Fine ArtGallo-Roman Museum at Fourvière, etc.

Lyon is considered France’s gastronomic capital. The city offers delicious cuisine for every budget from the city’s “bouchons” to the world famous chef Paul Bocuse.


Lyon official promotional video filmed from a drone.

Find everything you want to know about Lyon on the tourist office website.

socials.txt · Last modified: 2015/11/07 06:51 by ogeorgeo

Page Tools

BICA 2015 Sponsors

 liris univ-lyon1   

Sponsoring BICA 2015

Sponsoring BICA 2015 is a powerful way to advertise your company’s expertise and commitment to innovation in the domain of artificial intelligence and cognitive science.

The name of your company and its expertise will be displayed before, during, and after the conference. Not only your company will contribute to research and education, but it will also achieve tangible results in terms of promoting its activity, for example, with the objective of targeting new markets or recruiting new collaborators.

Please see our sponsoring opportunities in our sponsor’s guide:

For more information, feel free to contact Amélie Cordier and Olivier Georgeon.

Sub-events

Call for sub-event proposals

Proposal for sub-events are still open. Please contact Olivier GeorgeonAlexei Samsonovich, and Amélie Cordier.

Sub-events can relate to all areas relevant to BICA as stated in the Call for paper section.

Please indicate:

  • Type (symposium, workshop, tutorial, technology demo, panels, etc.)
  • Length (half-day or full day, preferably on November 6 unless you request otherwise)
  • Short abstract (including a call for contribution if applicable)
  • Keywords
  • Estimated number of participants
  • Does this sub-event accept specific paper submission?
  • Tentative program committee (if applicable)

Sub-event proposals are subject to approval by the core program committee.

Biological and Brain Foundations of Reservoir Computing

Keynote

  • Wolf Singer

Presentations

  • Joni Dambre
  • Bruno Golosio
  • Gregoire Pointeau

Dicussion mediator

Abstract

In reservoir computing, inputs are presented to a network of neurons with fixed recurrent connections (the reservoir). The recurrent connections yeild a dynamic system that generates a high dimensional mix in space and time of the input sequence. Modifiable connections to readout neurons are trained to generate the desired function of the input. First developed to describe prefrontal cortical neural activity during behavioral sequence learning, reservoirs have been used for advanced signal processing and to simulate neural activity in cortex. Recently, accumulating data indicate that the primate cortex behaves as a reservoir in its information processing capabilities. This symposium will address (a) recent findings that link reservoir activity to cortical activity in the behaving primate, and (b) how reservoirs can be used in cognitive architectures for higher cognitive functions like language processing.

submission

To submit your paper to this workshop, please follow the general instruction on the Submission page. Login to easychair as an author. Select track “Biological and Brain Foundations of Reservoir Computing”.

Developmental Learning Tutorial

  • Olivier Georgeon
  • Alain Mille
  • Florian Bernard
  • Rémi Cassado
  • Simon Gay

Developmental Learning consists of learning everything from scratch like a newborn baby. At the same time, the agent must discover the structure of its body, learn the structure of its environment, and develop its cognitive capabilities. Implementing an artificial system (robot) capable of such learning constitutes an immense challenge for the field of artificial intelligence.

We will introduce this tutorial by presenting the broad notion of artificial Agent Without Ontological Access to reality (AWOA). An AWOA agent is an agent whose input data is not a representation of the state of reality. Instead, the agent must construct a representation of reality dynamically from regularities observed in its stream of sensorimotor interactions.

Since an AWOA agent has no access to the state of reality or to a predefined representation of reality, it cannot learn to reach predefined states of reality, or to solve problems that are modeled by its designer beforehand. Instead, we expect AWOA agents to engage in open-ended learning by “sedimentation of habits”, which leads to developmental learning.

The game below gives you a glimpse into the problem of constructing a representation of reality from sensorimotor regularities. You are in the situation of a toddler who babbles ignoring the meaning of its sensorimotor experience, learning to gain control of its activity, and constructing knowledge of its world (its own body and its surrounding environment).

Biomimetic approaches for sustainable development

When ?

Friday, November 6th, 2-6PM.

Abstract

How can biological systems inspire our research about complex systems and help to contribute to sustainable development ? This workshop aims to gather multi-disciplinary researchers and make them identify cutting-edge topics in biomimetic approaches. The considered biomimetic approaches bridge the gap between the analysis of existing biological systems and some practical applications. The goal is to transfer some knowledge from the biological world to the resolution of complex issues in complex systems. (eg. Robots, Autonomous vehicles, smart cities). The workshop will be composed of two phases :

  1. In the first half, invited speakers from various research fields will present their recent work in biology (eg. Modeling of collective animal behaviours) and bio-inspired modeling of complex dynamical systems (eg. Human-robots interaction). A strong accent will be made on multi-disciplinary interactions.
  2. In a second phase, the discussion will focus on a current and future hot topic in sustainable development and smart mobility : connected and autonomous vehicles. After a general presentation from the traffic theory standpoint, the panel will discuss about potential applications of biomimetic approaches in order to solve critical issues :
    1. How should we model the behaviour of autonomous vehicles ?
    2. How to tackle the interactions between autonomous and human vehicles ?

Finally, the discussion of this half-day workshop will be extended to the smart city concept or other topics identified during the day.

Invited Speakers

  • Jean-Louis Deneubourg (Université Libre de Bruxelles)
  • Yven Duthen (Université Toulouse Capitole)
  • Nour-Eddin EL Faouzi (IFSTTAR)
  • Round Table : Christine Solnon (INSA Lyon), Bernard Favre (LUTB)

Program Commitee

  • Dr Romain Billot, Assistant Professor, LICIT, ENTPE (chairman).
  • Pr. Salima Hassas, Professor, LIRIS, University Lyon 1.
  • Dr. Thibault Prevost, French Ministry of Ecology, Sustainable Development and Energy.

Inscription

Participants who have been personally freely invited to the Biomimetic workshop may attend the workshop only. They are kindly invited to register to BICA2015 to attend the rest of this exciting conference.

Partners

liris entpe ifsttar univ-lyon1 medde

biomimetic.txt · Last modified: 2015/10/17 15:52 by romain

Page Tools

Symposium on Implications of Recent Results in Computational Narrative for BICA

This symposium will examine the intersection of the computational modeling of narrative (CMN) and biologically inspired cognitive architectures, and will comprise three talks. Symposium speakers will try to draw ideas and lessons relevant to BICA from current work in CMN.

Narrative Effects and Lessons for BICA
Mark Finlayson
Florida International University

Narrative is a ubiquitous language phenomenon that engages cognitive capabilities at multiple levels. I outline a number of observed effects that narrative has on cognitive processing, including improvements in comprehension, memory, and logical reasoning. Furthermore, an ability to understand narrative is critical to social reasoning. I connect these capabilities to recent results from the computational study of narrative, and draw a number of suggestions for biologically inspired cognitive architectures related to potential task domains, measurements of validity, and predicted cross-interactions among cognitive architectural components.

Towards Narratologically Inspired Cognitive Architectures
Nicolas Szilas
University of Geneva

For several decades, the hypothesis according to which narrative is not only a prominent form of human communication but also a fundamental way to represent knowledge and to structure the mind has been proposed and discussed. But surprisingly, this has not yield to any NICA (narratologically inspired cognitive architectures) and the hypothesis remains a fuzzy one with limited implications. Perhaps this is due to the fact that the few attempts to bridge the gap from narrative theory to cognitive architectures, namely the scripts and cases in artificial intelligence (AI), have considered only a small set of facets of narrative. Historically indeed, when AI and cognitive Science researchers tackled narrative in the 70s and 80s, they tended to reinvent narrative theories, ignoring the centuries of studies in the domain. In this contribution, we propose to study further the above hypothesis by identifying differentiating features of narratives that contrast with the classical problem solving AI and that may inspire new cognitive architectures. Potential applications of NICAs include better communicating machines, improved intelligent tutoring systems and robust knowledge bases.

Evolution-inspired Construction of Stories: Iterative Refinement of Narrative Drafts as a Social Cycle
Pablo Gervás & Carlos León
Universidad Complutense de Madrid

Narrative creation happens not only as an internal process in the writer’s mind, but also as a social phenomenon in which several individuals influence each other by creating, telling and evaluating the stories told in the community. As such, stories evolve over time under the influence of many activities: inventing new parts or rejecting old ones, changing the discourse, telling the plot in a different way, and changing the way the story is understood and accepted, possibly by other changes in the society. We propose a formal computational model based on the cognitive behavior of individuals inventing, telling and refining narrative structures based on the ICTIVS model. This new version of the model, Social-ICTIVS, adapts the previous model by considering each of the steps and re-defining them as a social activity of narrative evolution.

Logistics

Mark Finlayson, Chair
Florida International University

Presentation at this symposium will be by invitation only.

For invited speakers: to submit your talk abstract, please follow the general instruction on the Submission page. Login to easychair as an author and select this track.

Enaction, Complex Systems and Cognitive Architectures

Friday November 6, afternoon.

Chair

Leonardo Lana de Carvalho

Abstract

The enactive theory of cognition provided a portal for the design of new biologically inspired cognitive architectures. However, differently from cognitivism and connectionism, the enactive theory has not yet a prototypical computer model, despite of the wide variety of implementations that can illustrate the fundamental concepts of this approach. Nevertheless, a differential model of architecture in relation to cognitivist and connectionist architectures remains a great challenge. This point perseveres in the current research program in a very vividly way. Indeed, the construction of a world is sought, a way of being in the world. The agent would not be getting an informational input or a reinforcement, but the inputs would be better described as perturbations on a self-organizing complex systems. A prototypical model of enactive cognitive architecture is one of the largest challenges today.

With the aim of use the main concepts of this approach such as enaction, autopoiesis, structural coupling and natural drift, to review and increase computational approaches and models of cognitive architectures, we have proposed this workshop.

Program committee

  • Leonardo Lana de Carvalho
  • Ricardo Ribeiro Gudwin
  • Angelo Conrado Loula
  • João E. Kogler Jr.

Invited talk

  • Pierre De Loor

Submission

To submit your paper to this workshop, please follow the general instruction on the Submission page. Login to easychair as an author. Select track “Enaction, Complex Systems and Cognitive Architectures”.

enaction.txt · Last modified: 2015/06/08 10:49 by ogeorgeo

Page Tools

The Whole Brain Architecture Initiative

The Whole Brain Architecture Initiative (WBAI) is an NPO promoting research efforts to realize human-like AGI based on the WBA approach.

WBAI will have a paper presentation on a computational platform in the regular session at BICA 2015.

It will also have a separate session on the WBA approach:

Day 2: Saturday, November 7 5:30 pm – 6:30 pm
Chair: Tarek Besold
5:30pm-5:45pm Hiroshi Yamakawa
Intorduction to the Whole Brain Architecture
5:45pm-6:00pm Koichi Takahashi
Open development platforms for the Whole Brain Architecture Project
6:00pm-6:10pm Takeshi Itoh, Ayaka Kato & Jumpei Ukita
1st WBAI hackthon winners’ presentation –
Modeling the Development of Place Cells in Hippocampus
6:10pm-6:30pm Panel Discussions
“Is WBA whole brain simulation?”
Antonio Chella, Koichi Takahashi, Takashi Omori & Satoshi Kurihara

WBAI will be a BICA 2015 Sponsor and will have a ‘bare stand’ to visit.

Industry/Research meeting – Technology demo

French version available here.

Friday November 6 – 10:00am – 12:00am.

  • 10:00am – 11:00am: Pitches.
    • 10:10 Olivier Georgeon
    • 10:20 Guillaume Gibert
    • 10:30 Sherine Antoun
    • 10:40: Mark Waser
    • 10:50: Ignazio Infantino
  • 11:00am – 11:30am: Discussion panel (in French).
  • 11:30am – 12:00am: Demos.

This meeting will support synergies between research and industry by featuring demonstrations of innovative and creative technologies, including, but not limited to, the examples below.

Olivier Georgeon

Associate researcher at the LIRIS Université Claude Bernard Lyon 1. http://www.oliviergeorgeon.com/

Designing systems that learn habitudes of interaction

Olivier develops techniques for artificial systems to learn habits from regularities of interaction. Applications relate to any situation in which we wish an artificial system to learn habits from its interactions with humans, for example, domotics, companion robotics, software adaptation, end-user programming.

Guillaume Gibert

INSERM Lyon. http://www.sbri.fr/

Guillaume works on simulation and understanding of the cognitive mechanisms of sequential learning and language. Applications relate to improvement of human/robot collaboration.

Sherine Antoun

Associate Professeur at University of Illinois Springfield. Specialist of robotic perception through ultrasound in hostile environments.

Sherine works on positioning and navigation techniques adapted to ultrasound sensors for robots in hostile environments. Ultrasound sensors provide less information about the environment as compared to cameras or laser scanners, but they are less affected by visibility problems that often arise in hostile environments. Example applications are for work and rescue in fire situations, and assistance to visually impaired persons.

Mark Waser

Mark is CTO of the Digital Wisdom Institute and D161T4L W15DOM INC (http://wisdom.digital), organizations devoted to the ethical implementation of advanced technologies for the benefit of all. He has 35 years of experience in software systems architecture, design & development, publishing data science research since 1983 and developing commercial AI software since 1984, ranging from expert systems for Citicorp to neural networks for the Air Force. Mr. Waser has a BA (Biochemistry/Philosophy), an MSE (Artificial Intelligence) and doctoral studies in Machine Learning/Human Decision-Making. He is particularly interested in safe ethical architectures and motivational systems for intelligent machines (including humans).

Ignazio Infantino

Istituto di Calcolo e Reti ad Alte Prestazioni, Consiglio Nazionale delle Ricerche.

http://www.pa.icar.cnr.it/infantino/

Cognitive Architecture + Computational Creativity = Artificial Painter

Nao robot acts by means of our cognitive architecture (CA) for computational creativity (CC) based on the Psi model and on the mechanisms inspired by the dual process theories of reasoning and rationality. In recent years, we have developed various modules of the cognitive architecture that allows a robot to execute creative paintings during a human-robot interaction session. In the recent work we have designed and implemented a dual process-based mechanism of computational creativity, hypothesizing the interaction between two types of reasoning for the realization of a creative artifact. Such integration allowed us to refine some relevant mechanisms in the previous CA, allowing the robot to produce interesting artworks by exploring the potentialities of a cognitively-inspired artificial creative thinking.

Ignazio Infantino, Agnese Augello, Giovanni Pilato, Filippo Vella, Riccardo Rizzo (Institute of High Performance Computing and Networking – National Research Council ICAR-CR). Antonio Lieto (Department of Computer Science, University of Turin).