Artificial Evolution of Plastic Neural Networks: A Few Key Concepts

Mouret, Jean-Baptiste; Tonelli, Paul

doi:10.1007/978-3-642-55337-0_9

Cited by 19 publications

(14 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Online adaptation refers to a robustness or ability to adapt to internal or external perturbations or changes in input and output ranges; in other words, the ability to maintain homeostasis. These latter two definitions are very similar to terms defined by Mouret and Tonelli [19]: an agent is said to possess behavioural robustness, which is akin to online adaptation, when it can maintain the same qualitative behaviour despite environmental or morphological changes; and an agent is said to exhibit behavioural change, which is akin to online learning, when in a reward-based environment a change in reward causes it to…”

Section: Introductionmentioning

confidence: 84%

Evolving Plastic Neural Networks for Online Learning: Review and Future Directions

Coleman

Blair

2012

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Recent years have seen a resurgence of interest in evolving plastic neural networks for online learning. These approaches have an intrinsic appeal -since, to date, the only working example of general intelligence is the human brain, which has developed through evolution, and exhibits a great capacity to adapt to unfamiliar environments. In this paper we review prior work in this area -including problem domains and tasks, fitness functions, synaptic plasticity models and neural network encoding schemes. We conclude with a discussion of current findings and promising future directions, including incorporation of functional properties observed in biological neural networks which appear to play a role in learning processes, and addressing the "general" in general intelligence by the introduction of previously unseen tasks during the evolution process.

show abstract

Section: Introductionmentioning

confidence: 84%

Evolving Plastic Neural Networks for Online Learning: Review and Future Directions

Coleman

Blair

2012

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Their discrete parts can be found in Table 3. RuleID 1 2 3 4 5 6 7 8 9 10 11 12 13 14 Table 3: A complete list of 15 distinct evolved DSP rules given by the columns ∆w 1 through ∆w 15 . Their continuous parts can be found in Table 2.…”

Section: Discussionmentioning

confidence: 99%

“…Plasticity in EPANNs makes them capable of learning during their lifetime by changing their configuration [2,15,22]. Hebbian learning rules are often employed to model plasticity in EPANNs.…”

Section: Evolving Plastic Artificial Neural Networkmentioning

confidence: 99%

Learning with delayed synaptic plasticity

Yaman

Iacca

Mocanu

et al. 2019

Proceedings of the Genetic and Evolutionary Computation Conference

View full text Add to dashboard Cite

The plasticity property of biological neural networks allows them to perform learning and optimize their behavior by changing their configuration. Inspired by biology, plasticity can be modeled in artificial neural networks by using Hebbian learning rules, i.e. rules that update synapses based on the neuron activations and reinforcement signals. However, the distal reward problem arises when the reinforcement signals are not available immediately after each network output to associate the neuron activations that contributed to receiving the reinforcement signal. In this work, we extend Hebbian plasticity rules to allow learning in distal reward cases. We propose the use of neuron activation traces (NATs) to provide additional data storage in each synapse to keep track of the activation of the neurons. Delayed reinforcement signals are provided after each episode relative to the networks' performance during the previous episode. We employ genetic algorithms to evolve delayed synaptic plasticity (DSP) rules and perform synaptic updates based on NATs and delayed reinforcement signals. We compare DSP with an analogous hill climbing algorithm that does not incorporate domain knowledge introduced with the NATs, and show that the synaptic updates performed by the DSP rules demonstrate more effective training performance relative to the HC algorithm. CCS CONCEPTS• Theory of computation → Evolutionary algorithms; Bioinspired optimization; KEYWORDSEvolving plastic artificial neural networks, Hebbian learning, delayed plasticity, distal reward problem

show abstract

“…A challenge for EPANNs is to acquire general learning abilities in which the network is capable of learning problems not encountered during evolution. Mouret and Tonelli (2014) propose the distinction between the evolution of behavioral switches and the evolution of synaptic general learning abilities, and suggest conditions that favor these types of learning. General learning can be intuitively understood as the capability to learn any association among input, internal, and output patterns, both in the spatial and temporal dimensions, regardless of the complexity of the problem.…”

Section: B Evolving General Learningmentioning

confidence: 99%

Born to learn: The inspiration, progress, and future of evolved plastic artificial neural networks

2018

View full text Add to dashboard Cite

Biological neural networks are systems of extraordinary computational capabilities shaped by evolution, development, and lifelong learning. The interplay of these elements leads to the emergence of biological intelligence. Inspired by such intricate natural phenomena, Evolved Plastic Artificial Neural Networks (EPANNs) employ simulated evolution in-silico to breed plastic neural networks with the aim to autonomously design and create learning systems. EPANN experiments evolve networks that include both innate properties and the ability to change and learn in response to experiences in different environments and problem domains. EPANNs' aims include autonomously creating learning systems, bootstrapping learning from scratch, recovering performance in unseen conditions, testing the computational advantages of particular neural components, and deriving hypotheses on the emergence of biological learning. Thus, EPANNs may include a large variety of different neuron types and dynamics, network architectures, plasticity rules, and other factors. While EPANNs have seen considerable progress over the last two decades, current scientific and technological advances in artificial neural networks are setting the conditions for radically new approaches and results. Exploiting the increased availability of computational resources and of simulation environments, the often challenging task of hand-designing learning neural networks could be replaced by more autonomous and creative processes. This paper brings together a variety of inspiring ideas that define the field of EPANNs. The main methods and results are reviewed. Finally, new opportunities and possible developments are presented.

show abstract

Artificial Evolution of Plastic Neural Networks: A Few Key Concepts

Cited by 19 publications

References 28 publications

Evolving Plastic Neural Networks for Online Learning: Review and Future Directions

Evolving Plastic Neural Networks for Online Learning: Review and Future Directions

Learning with delayed synaptic plasticity

Born to learn: The inspiration, progress, and future of evolved plastic artificial neural networks

Contact Info

Product

Resources

About