The evolution of a generalized neural learning rule
Published 1 July 2016
Jeff Orchard, Lin Wang
Citations16
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
This paper aims to evolve a more general learning rule, and since neural networks are so versatile, it construct the learning function itself out of a neural network.
Abstract
Evolution is extremely creative. The mere availability of a mechanism for synaptic change seems to be enough for evolution to derive a learning rule. Many simulations of evolution have evolved learning in a highly guided manner. Either by constraining the update function to a Hebbian form, or by supplying an error/teaching signal. In this paper, we aim to evolve a more general learning rule. And since neural networks are so versatile, we construct the learning function itself out of a neural network. Our evolved networks excel at the foraging task they evolved in. Amazingly, they even function robustly when tested outside of their historical niche. The same cannot be said for the Hebbian learning networks we compare to.
Keywords
Computer Science
Neural ComputationA Fast Learning Algorithm for Deep Belief Nets
16,404 Citations2006Geoffrey E. Hinton, Simon Osindero +1 more
A fast, greedy algorithm is derived that can learn deep, directed belief networks one layer at a time, provided the top two layers form an undirected associative memory.
ScienceDistilling Free-Form Natural Laws from Experimental Data
2,847 Citations2009Michael Schmidt, Hod Lipson
This work proposes a principle for the identification of nontriviality, and demonstrated this approach by automatically searching motion-tracking data captured from various physical systems, ranging from simple harmonic oscillators to chaotic double-pendula, and discovered Hamiltonians, Lagrangians, and other laws of geometric and momentum conservation.
Adaptive BehaviorLearning and Evolution in Neural Networks
350 Citations1994Stefano Nolfi, Domenico Parisi +1 more
Simulation on populations of neural networks that both evolve at the population level and learn at the individual level finds both individuals that have high fitness and individuals that, although they do not have high Fitness at birth, end up with high fitness because they learn to predict.
Elsevier eBooksThe Evolution of Learning: An Experiment in Genetic Connectionism
196 Citations1991David J. Chalmers
A general framework for the evolution of learning is outlined, and is applied to the task of evolving mechanisms suitable for supervised learning in single-layer neural networks.
Adaptive BehaviorEvolution of Reinforcement Learning in Uncertain Environments: A Simple Explanation for Complex Foraging Behaviors
159 Citations2002Y. Niv, Daphna Joel +2 more
Loughborough University Institutional Repository (Loughborough University)Evolutionary Advantages of Neuromodulated Plasticity in Dynamic, Reward-based Scenarios
121 Citations2008Andrea Soltoggio, John A. Bullinaria +3 more
It is concluded that modulatory neurons evolve autonomously in the proposed learning tasks, allowing for increased learning and memory capabilities.
Evolving adaptive neural networks with and without adaptive synapses
109 Citations2004Kenneth O. Stanley, Bobby D. Bryant +1 more
The surprising experimental result is that the former method can be more effective than evolving networks with dynamic weights, calling into question the intuitive notion that networks withynamic synapses are necessary for evolving solutions to adaptive tasks.
Lecture notes in computer scienceIndirectly Encoding Neural Plasticity as a Pattern of Local Rules
76 Citations2010Sebastian Risi, Kenneth O. Stanley
This paper aims to show that learning rules can be effectively indirectly encoded by extending the Hypercube-based NeuroEvolution of Augmenting Topologies (HyperNEAT) method to evolve large-scale adaptive ANNs, which is a major goal for neuroevolution.
Evolution and design of distributed learning rules
49 Citations2002Thomas Philip Rúnarsson, Magnus Jönsson
Experimental results show that a learning rule of this type is very capable of generating an efficient training algorithm.
Lecture notes in computer scienceEvolving Plastic Neural Networks for Online Learning: Review and Future Directions
19 Citations2012Oliver J. Coleman, Alan Blair
Prior work in evolving plastic neural networks for online learning is reviewed, including problem domains and tasks, fitness functions, synaptic plasticity models and neural network encoding schemes, and addressing the "general" in general intelligence by the introduction of previously unseen tasks during the evolution process.
On the relationships between synaptic plasticity and generative systems
18 Citations2011Paul Tonelli, Jean-Baptiste Mouret
Results are reported of a set of experiments designed to check that (1) synaptic plasticity can help a GDS to fine-tune synaptic weights and (2) that with the investigated generative encoding (EvoNeuro), only a few learning scenarios are necessary to evolve a general learning system, which can adapt itself to reward-based scenarios not tested during the fitness evaluation.