Neuromorphic Embodied Agents that Learn (NEAL) is a part of the Human Brain Project

European Grant 604102 (Chris Huyck and Ian Mitchell)

In the first phase of NEAL, the existing CABot3 agent is being translated from its Java based Fatiguing Leaky Integrate and Fire neural model, to more standard neural models used in PyNN. The agent moves about in a virtual environment, takes natural language commands, plans, and learns cognitive maps. The translated version will run on the SpiNNaker and HICANN neuromorphic chips.

In the second phase, once translated, the agent will be expanded. It will learn new visual categories from the environment, and new plans. Its cell assembly based memories will be more psychologically realistic, and the system will include cognitive models for common tasks.

Evolution as an Information Dynamic System

EPSRC grant EP/H031936/1 (Roman Belavkin, John Aston (Warwick), Alastair Channon (Keel), Chris Knight (Manchester))

The project aims at developing better understanding of the laws of evolution using information dynamics theory. Heredity and mutation are viewed as parameters of an adaptive system, which vary according to changes in information about the environment and fitness. The project is in collaboration with John Aston (University of Warwick, Statistics), Alastair Channon (University of Keele, Computing and Mathematics) and Chris Knight (University of Manchester, Life Sciences).


EPSRC grant EP/D059720 (Christian Huyck, Roman Belavkin)

The EPSRC has funded a project to develop an agent based on cell assemblies that communicates via natural language, senses the environment and assists the user.

Mind and Brain Architectures


Geetha Abeysinghe and Christian Huyck

This is an EPSRC funded project which aims to develop a Natural Language Processing system, which can convert a business process description in free text to an executable formal notation. The graphical models of the business process produced by the execution will then be used for verification and further elicitation of the business process. The work on the project will begin in late July/early August.

Cognitive Systems

Roman Belavkin

Cognitive Systems is a general group involving multidisciplinary collaboration on building cognitive systems.

Cross Language Information Retrieval

Viviane Orengo and Chris Huyck

Digitized text is stored in many languages. When searching for information, the user may need a document that is in a language in which he is not fluent. Multi-lingual thesauri and large multi-lingual corpora can be used to develop tools that can enable a user to search documents in languages in which he is not fluent.

Traveling Salesman and GAs

Ian Mitchell

The technique, essentially, relies on each node on the TSP graph sending messages to all possible other nodes in parallel, such a technique exploits the collision of messages. A genetic algorithm is introduced to optimise the search space. The use of temporal representations used to solve the TSP has no illegal representations encoded in the gene and hence repair algorithms are unnecessary. This paper investigates the exploitation of message collision, the post collision process and how certain sequences of events yield a near optimal solution to the TSP.

Hebbian Cell Assemblies

Chris Huyck

The CANT (Connections, Associations and Network Technology) model is designed to function like a natural neural system. The basic idea is derived from Hebb's idea of the Cell Assembly, a reverberating circuit of neurons which is the neural equivalent of a concept. The long-term goal of the model is to discover how CAs work; discover what CAs can do; duplicate psychological data with CAs.

Sequence Recognition using Neural Nets

Ian Mitchell and Siri Bavan

Given a non-orthogonal training set, recall a sequence from an ambiguous stimulus. This usually results in a winner-takes-all approach, whereby each solution competes until the strongest signal wins. The winner is proposed as the final solution, however how correct it is depends on its use. Information retrieval rarely results in a single output and therefore emphasis is being placed on techniques capable of retrieving multiple memories. At present many retrieval methods rank their results, however many sequences can have equivalent ranking i.e. they are all candidate solutions. It is this problem domain that this project investigates.