From modulated Hebbian plasticity to simple behavior learning through noise and weight saturation

Authors:
Andrea Soltoggio;Kenneth O. Stanley
Affiliations:
Research Institute for Cognition and Robotics, University of Bielefeld, Germany;Department of Electrical Engineering and Computer Science, University of Central Florida, USA
Venue:
Neural Networks
Year:
2012

Citing 20
Cited 1

Computation at the edge of chaos: phase transitions and emergent computation

Computation at the edge of chaos: phase transitions and emergent computation
Runaway synaptic modification in models of cortex: implications for Alzheimer's disease

Neural Networks
The role of constraints in Hebbian learning

Neural Computation
Computational models of neuromodulation

Neural Computation
Metalearning and neuromodulation

Neural Networks - Computational models of neuromodulation
Neuromodulation and Plasticity in an autonomous robot

Neural Networks - Computational models of neuromodulation
Evolving neural networks through augmenting topologies

Evolutionary Computation
A proposed function for Hippocampal theta rhythm: separate phases of encoding and retrieval enhance reversal of prior learning

Neural Computation
Evolution of reinforcement learning in uncertain environments: a simple explanation for complex foraging behaviors

Adaptive Behavior
On the computational power of circuits of spiking neurons

Journal of Computer and System Sciences
The Cyber Rodent Project: Exploration of Adaptive Mechanisms for Self-Preservation and Self-Reproduction

Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Spike-Driven Synaptic Plasticity: Theory, Simulation, VLSI Implementation

Neural Computation
Strongly improved stability and faster convergence of temporal sequence learning by using input correlations only

Neural Computation
Strongly improved stability and faster convergence of temporal sequence learning by using input correlations only

Neural Computation
Reinforcement Learning Through Modulation of Spike-Timing-Dependent Synaptic Plasticity

Neural Computation
Learning with “Relevance”: Using a Third Factor to Stabilize Hebbian Learning

Neural Computation
The Neuromodulatory System: A Framework for Survival and Adaptive Behavior in a Challenging World

Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Stimulus representation and the timing of reward-prediction errors in models of the dopamine system

Neural Computation
Reward-modulated hebbian learning of decision making

Neural Computation
Solving the distal reward problem with rare correlations

Neural Computation

Solving the distal reward problem with rare correlations

Neural Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

Synaptic plasticity is a major mechanism for adaptation, learning, and memory. Yet current models struggle to link local synaptic changes to the acquisition of behaviors. The aim of this paper is to demonstrate a computational relationship between local Hebbian plasticity and behavior learning by exploiting two traditionally unwanted features: neural noise and synaptic weight saturation. A modulation signal is employed to arbitrate the sign of plasticity: when the modulation is positive, the synaptic weights saturate to express exploitative behavior; when it is negative, the weights converge to average values, and neural noise reconfigures the network's functionality. This process is demonstrated through simulating neural dynamics in the autonomous emergence of fearful and aggressive navigating behaviors and in the solution to reward-based problems. The neural model learns, memorizes, and modifies different behaviors that lead to positive modulation in a variety of settings. The algorithm establishes a simple relationship between local plasticity and behavior learning by demonstrating the utility of noise and weight saturation. Moreover, it provides a new tool to simulate adaptive behavior, and contributes to bridging the gap between synaptic changes and behavior in neural computation.