A Spiking Neural Learning Classifier System

Details A Spiking Neural Learning Classifier System A Spiking Neural Learning Classifier System

2012-01-16

arxiv.org/abs/1201.3249v1

Computer Science

Neural and Evolutionary Computing

20 pages

Scientific paper

Learning Classifier Systems (LCS) are population-based reinforcement learners used in a wide variety of applications. This paper presents a LCS where each traditional rule is represented by a spiking neural network, a type of network with dynamic internal state. We employ a constructivist model of growth of both neurons and dendrites that realise flexible learning by evolving structures of sufficient complexity to solve a well-known problem involving continuous, real-valued inputs. Additionally, we extend the system to enable temporal state decomposition. By allowing our LCS to chain together sequences of heterogeneous actions into macro-actions, it is shown to perform optimally in a problem where traditional methods can fail to find a solution in a reasonable amount of time. Our final system is tested on a simulated robotics platform.

Affiliated with

Also associated with

No associations

Rating

A Spiking Neural Learning Classifier System does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with A Spiking Neural Learning Classifier System, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and A Spiking Neural Learning Classifier System will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-410090