スパイキングニューラル学習分類器システム
A Spiking Neural Learning Classifier System
各ルールをスパイキングニューラルネットで表現し、ニューロンと樹状突起の成長を進化的に構築する学習分類器システムを提案。連続値入力問題や時系列状態分解、ロボティクスシミュレーションで有効性を示した。
著者: Gerard Howard, Larry Bull, Pier-Luca Lanzi
分類: cs.NE, cs.LG, cs.RO
原文アブストラクト
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.
