background preloader

Cognitive architecture

Cognitive architecture
Distinctions[edit] Some well-known cognitive architectures[edit] See also[edit]

Liste de concepts logiques Un article de Wikipédia, l'encyclopédie libre. Cet article liste les principaux concepts logiques, au sens philosophique du terme, c'est-à-dire en logique générale (issue de la dialectique). Nota : Liste des concepts logiques de la philosophie Biologically inspired cognitive architectures Biologically Inspired Cognitive Architectures (BICA) was a DARPA project administered by the Information Processing Technology Office (IPTO) which began in 2005 and is designed to create the next generation of Cognitive architecture models of human artificial intelligence. Its first phase (Design) ran from September 2005 to around October 2006, and was intended to generate new ideas for biological architectures that could be used to create embodied computational architectures of human intelligence. The second phase (Implementation) of BICA was set to begin in the spring of 2007, and would have involved the actual construction of new intelligent agents that live and behave in a virtual environment. However, this phase was canceled by DARPA, reportedly because it was seen as being too ambitious.[1] Now BICA is a transdisciplinary study that aims to design, characterise and implement human-level cognitive architectures. External links[edit] References[edit]

Marvin Minsky Marvin Lee Minsky (born August 9, 1927) is an American cognitive scientist in the field of artificial intelligence (AI), co-founder of Massachusetts Institute of Technology's AI laboratory, and author of several texts on AI and philosophy.[6][7][9][10][11][12][13][14][15][16][17] Biography[edit] Isaac Asimov described Minsky as one of only two people he would admit were more intelligent than he was, the other being Carl Sagan.[22] Probably no one would ever know this; it did not matter. In the 1980s, Minsky and Good had shown how neural networks could be generated automatically—self replicated—in accordance with any arbitrary learning program. In the early 1970s at the MIT Artificial Intelligence Lab, Minsky and Seymour Papert started developing what came to be called The Society of Mind theory. Awards and affiliations[edit] Marvin Minsky is affiliated with the following organizations: Minsky is a critic of the Loebner Prize.[36][37] Personal life[edit] Minsky is an atheist.[39]

Perceptron The perceptron algorithm was invented in 1957 at the Cornell Aeronautical Laboratory by Frank Rosenblatt.[1] Definition[edit] The perceptron is a binary classifier which maps its input (a real-valued vector) to an output value (a single binary value): where is a vector of real-valued weights, is the dot product (which here computes a weighted sum), and is the 'bias', a constant term that does not depend on any input value. The value of (0 or 1) is used to classify as either a positive or a negative instance, in the case of a binary classification problem. is negative, then the weighted combination of inputs must produce a positive value greater than in order to push the classifier neuron over the 0 threshold. In the context of artificial neural networks, a perceptron is an artificial neuron using the Heaviside step function as the activation function. Learning algorithm[edit] Below is an example of a learning algorithm for a (single-layer) perceptron. Definitions[edit] To represent the weights: 1. .

The Emotion Machine The Emotion Machine: Commonsense Thinking, Artificial Intelligence, and the Future of the Human Mind [1] is a book by cognitive scientist Marvin Lee Minsky. The book is a sequel to Minsky's earlier book Society of Mind. Minsky argues that emotions are different ways to think that our mind uses to increase our intelligence. Reviews[edit] In a book review for the Washington Post, neurologist Richard Restak states that:[3] Minsky does a marvelous job parsing other complicated mental activities into simpler elements. ... Outline[edit] Minsky outlines the book as follows:[citation needed] "We are born with many mental resources."" Other reviews[edit] Author's Prepublication Draft[edit] External links[edit] References[edit]

Réseau de concepts Un article de Wikipédia, l'encyclopédie libre. Pour les articles homonymes, voir Réseau. En mathématiques, un réseau de concepts est un graphe entièrement connexe dont les nœuds ont une valeur symbolique (un texte, une chaîne de caractères), et une activation. Les liens entre ces nœuds sont pondérés et orientés, de sorte qu'ils puissent représenter l'influence d'un nœud sur un autre. Définition[modifier | modifier le code] Le réseau de concepts est le modèle de BAsCET, il correspond au Slipnet de Copycat; une de ses particularités est d'être dynamique, c'est-à-dire qu'il évolue au cours du temps pour s'adapter au problème. On peut dire qu'il fonctionne par association de nœuds (si un nœud est actif et qu'il est fortement lié à un autre nœud, il l'activera), et par extension, si l'on construit le réseau de concepts d'une certaine manière, par association de symboles et émergence de concepts. Chaque nœud du réseau possède les champs suivants : symbole (S) importance conceptuelle (IC) agents (Ag)

Emotion Machine: Commonsense Thinking, Artificial Intelligence, and the Future of the Human Mind | MIT World Ricardo Sanz Home Page - Biologically Inspired Cognitive Architectures 2011 The Biologically Inspired Cognitive Architectures 2011 Conference took place at Washington, USA on 4-6 November 2011. The challenge of creating a real-life computational equivalent of the human mind calls for our joint efforts to better understand at a computational level how natural intelligent systems develop their cognitive and learning functions. BICA conference grew up from a AAAI Fall symposium, focusing on the emergent hot topics in computer, brain and cognitive sciences unified by the challenge of replicating the human mind in a computer. In this event we presented a general model of emotion based on the interpretation of emotional processes as control reorganisations driven by values. Concurrent control patterns deployed over neural components. Adaptive systems use feedback as a key strategy to cope with uncertainty and change in their environments. Get the slides of the talk.

Autonomous Systems Laboratory - Home An ASLab Research Seminar for Autonomous Systems Ricardo Sanz Place: Aula de Seminarios de Automática Time: December 12, 2013 / 12:30-14:00 Our lives depend on the technical infrastructure that surrounds us. The contemporary -beginnings of XXI century- human ecosystem is composed not just of our preys, our predators, the fruits to gather and the inclement climate. Henceforth, the human impact derived from the failure of these systems is becoming enormously severe, threatening the economy, the security of nations and organisations, the equilibrium of the environment and even the safety of human individuals. We are interested in these technological systems and how to improve their operational profile. We are interested in technology for making systems autonomous, and, in this context, a topic of research is how to achieve "robust autonomy". Said this way, the purpose of robust autonomy is, basically, the same as the purpose of any controller. Find more about Ricardo Sanz.

Scientists Afflict Computers with Schizophrenia to Better Understand the Human Brain May 5, 2011 AUSTIN, Texas — Computer networks that can't forget fast enough can show symptoms of a kind of virtual schizophrenia, giving researchers further clues to the inner workings of schizophrenic brains, researchers at The University of Texas at Austin and Yale University have found. The researchers used a virtual computer model, or "neural network," to simulate the excessive release of dopamine in the brain. They found that the network recalled memories in a distinctly schizophrenic-like fashion. Their results were published in April in Biological Psychiatry. "The hypothesis is that dopamine encodes the importance — the salience — of experience," says Uli Grasemann, a graduate student in the Department of Computer Science at The University of Texas at Austin. The neural network used by Grasemann and his adviser, Professor Risto Miikkulainen, is called DISCERN. In order to model the process, Grasemann and Miikkulainen began by teaching a series of simple stories to DISCERN.

Introduction JAYET Arnaud Maîtrise de sciences cognitives Année 2002 – 2003 « Affective Computing » : Apport des Processus Emotionnels aux Systèmes Artificiels. Mémoire codirigé par Messieurs : Henrique SEQUEIRA Professeur de Neurosciences, Université des Sciences et Technologies de Lille I Fabien TORRE Maître de Conférence, Université de Lille III – Charles de Gaulle Laboratoire GRAPPA Table des matières. 3 Conclusion 14 4.4 Réseaux de neurones formels et émotions. 37 Introduction L’homme n’a eut de cesse d’essayer de créer, au fil des âges, un être à son image. Dans les années 1940, la conception de l’homme va prendre un nouveau tour avec les travaux de Alan Turing et Von Neumann qui vont servir de base aux tout premiers ordinateurs. Cependant, les travaux de Freud (1856 – 1939), de Darwin (1809 – 1882) ou encore de biologistes comme James Lang ou plus récemment de Damasio apporte un nouvel aspect au fonctionnement humain. Partie I : Questions préliminaires - Que recouvre la « modélisation émotionnelle » ? Début

In Natural Networks, Strength in Loops Examine the delicate branching patterns on a leaf or a dragonfly’s wing and you’ll see a complex network of nested loops. This pattern can be found scattered throughout nature and structural engineering: in the brain’s cerebral vasculature, arrays of fungi living underground, the convoluted shape of a foraging slime mold and the metal bracings of the Eiffel Tower. The Eiffel Tower incorporates many nested loops, designed to distribute strain over the structure. Loop architectures, like redundant computer networks or electrical grids, make structures resistant to damage. “We understand the physics of the connections between entities in full, disgusting detail,” Magnasco said of simple circulatory systems. Over the past few years, Magnasco and others have begun to explore exactly why these patterns are so commonly found in nature. To Build a Leaf Marcelo Magnasco VIDEO: Thanks to the resilient structure of the loop network, fluid can reach all parts of a damaged leaf. Mapping Blood Vessels