Spike-Timing Dependent Competitive Learning of Integrate-and-Fire Neurons with Active Dendrites

Panchev, Christo; Wermter, Stefan; Chen, Huixin

doi:10.1007/3-540-46084-5_145

Cited by 16 publications

(9 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The question of differently shaped weight change curves is of relevance for aspects of dendritic synaptic development and, consequentially, also for dendritic computations. Therefore some groups have started to address this problem by explicitly parameterizing weight change curves along dendritic structures (Panchev et al, 2002;Sterratt and van Ooyen, 2002).…”

Section: Critique Of the Biophysical Stdp Modelsmentioning

confidence: 99%

Temporal Sequence Learning, Prediction, and Control: A Review of Different Models and Their Relation to Biological Mechanisms

2005

View full text Add to dashboard Cite

In this article we compare methods for temporal sequence learning (TSL) across the disciplines machine-control, classical conditioning, neuronal models for TSL as well as spiketiming dependent plasticity. This review will briefly introduce the most influential models and focus on two questions: 1) To what degree are reward-based (e.g. TD-learning) and correlation based (hebbian) learning related? and 2) How do the different models correspond to possibly underlying biological mechanisms of synaptic plasticity? We will first compare the different models in an open-loop condition, where behavioral feedback does not alter the learning. Here we observe, that reward-based and correlation based learning are indeed very similar. Machine-control is then used to introduce the problem of closed-loop control (e.g. "actor-critic architectures"). Here the problem of evaluative ("rewards") versus nonevaluative ("correlations") feedback from the environment will be discussed showing that both learning approaches are fundamentally different in the closed-loop condition. In trying to answer the second question we will compare neuronal versions of the different learning architectures to the anatomy of the involved brain structures (basal-ganglia, thalamus and cortex) and to the molecular biophysics of glutamatergic and dopaminergic synapses. Finally we discuss the different algorithms used to model spike-timing dependent plasticity (STDP) and compare them to reward based learning rules. Certain similarities are found in spite of the strongly different time scales. Here we focus on the biophysics of the different Calcium-release mechanisms known to be involved in STDP.

show abstract

Section: Critique Of the Biophysical Stdp Modelsmentioning

confidence: 99%

Temporal Sequence Learning, Prediction, and Control: A Review of Different Models and Their Relation to Biological Mechanisms

2005

View full text Add to dashboard Cite

show abstract

“…Neurite branches are allowed to grow and shrink, and communicate with each other via synapses. Dendrites [8], synaptic dynamics [7] and synaptic communication have been included to enhance the capabilities of the computational network. The network we described has the potential virtue that it is autonomous in the sense that when the compartmentalised chromosomal programs are run a network of neurons, neurites and synapses grows in response to its own internal dynamics and the agents environmental experiences.…”

Section: Introductionmentioning

confidence: 99%

Coevolution of intelligent agents using cartesian genetic programming

Khan

Miller

Halliday

2007

Proceedings of the 9th Annual Conference on Genetic and Evolutionary Computation

View full text Add to dashboard Cite

A coevolutionary competitive learning environment for two antagonistic agents is presented. The agents are controlled by a new kind of computational network based on a compartmentalised model of neurons. The genetic basis of neurons is an important [27] and neglected aspect of previous approaches. Accordingly, we have defined a collection of chromosomes representing various aspects of the neuron: soma, dendrites and axon branches, and synaptic connections. Chromosomes are represented and evolved using a form of genetic programming (GP) known as Cartesian GP. The network formed by running the chromosomal programs, has a highly dynamic morphology in which neurons grow, and die, and neurite branches together with synaptic connections form and change in response to environmental interactions. The idea of this paper is to demonstrate the importance of the genetic transfer of learned experience and life time learning. The learning is a consequence of the complex dynamics produced as a result of interaction (coevolution) between two intelligent agents. Our results show that both agents exhibit interesting learning capabilities.

show abstract

“…To copy otherwise, to republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. GECCO'07, July [7][8][9][10][11]2007, London, England, United Kingdom. Copyright 2007 ACM 978-1-59593-698-1/07/0007 ...$5.00.…”

Section: Introductionmentioning

confidence: 99%

“…The branches can self-prune [4], [5], and can produce new branches to get an optimized network that depend on the complexity of the problem. In the model, a neuron consists of a soma, dendrites [10], and axons with branches and dynamic synapses [9] and synaptic communication. Neurons are placed in a grid to give branches a sense of virtual proximity.…”

Section: Introductionmentioning

confidence: 99%

A developmental model of neural computation using cartesian genetic programming

Khan

Miller

Halliday

2007

Proceedings of the 9th Annual Conference Companion on Genetic and Evolutionary Computation

View full text Add to dashboard Cite

The brain has long been seen as a powerful analogy from which novel computational techniques could be devised. However, most artificial neural network approaches have ignored the genetic basis of neural functions. In this paper we describe a radically different approach. We have devised a compartmental model of a neuron as a collection of seven chromosomes encoding distinct computational functions representing aspects of real neurons. This model allows neurons, dendrites, and axon branches to grow, die and change while solving a computational problem. This also causes the synaptic morphology to change and affect the information processing. Since the appropriate computational equivalent functions of neural computation are unknown, we have used a form of genetic programming known as Cartesian Genetic Programming (CGP) to obtain these functions. We have evaluated the learning potential of this system in the context of solving a well known agent based learning scenario, known as wumpus world and obtained promising results.

show abstract

Spike-Timing Dependent Competitive Learning of Integrate-and-Fire Neurons with Active Dendrites

Cited by 16 publications

References 5 publications

Temporal Sequence Learning, Prediction, and Control: A Review of Different Models and Their Relation to Biological Mechanisms

Temporal Sequence Learning, Prediction, and Control: A Review of Different Models and Their Relation to Biological Mechanisms

Coevolution of intelligent agents using cartesian genetic programming

A developmental model of neural computation using cartesian genetic programming

Contact Info

Product

Resources

About