Born to Learn: the Inspiration, Progress, and Future of Evolved Plastic Artificial Neural Networks

@article{Soltoggio2018BornTL,
  title={Born to Learn: the Inspiration, Progress, and Future of Evolved Plastic Artificial Neural Networks},
  author={Andrea Soltoggio and Kenneth O. Stanley and Sebastian Risi},
  journal={Neural networks : the official journal of the International Neural Network Society},
  year={2018},
  volume={108},
  pages={
          48-67
        }
}
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… Expand
Evolution of Biologically Inspired Learning in Artificial Neural Networks
TLDR
The final author version and the galley proof are versions of the publication after peer review that features the final layout of the paper including the volume, issue and page numbers. Expand
Evolving Plasticity for Autonomous Learning under Changing Environmental Conditions
TLDR
This work uses a discrete representation to encode the learning rules in a finite search space, and employs genetic algorithms to optimize these rules to allow learning on two separate tasks (a foraging and a prey-predator scenario) in online lifetime learning settings. Expand
Differentiable plasticity: training plastic neural networks with backpropagation
TLDR
It is shown that plasticity, just like connection weights, can be optimized by gradient descent in large (millions of parameters) recurrent networks with Hebbian plastic connections, and it is concluded that differentiable plasticity may provide a powerful novel approach to the learning-to-learn problem. Expand
EVOLVING SELF-TAUGHT NEURAL NETWORKS: THE BALDWIN EFFECT AND THE EMERGENCE OF INTELLIGENCE
The so-called Baldwin Effect generally says how learning, as a form of ontogenetic adaptation, can influence the process of phylogenetic adaptation, or evolution. This idea has also been taken intoExpand
Evolving Self-taught Neural Networks: The Baldwin Effect and the Emergence of Intelligence
  • N. Le
  • Computer Science
  • ArXiv
  • 2019
TLDR
Experimental results show that the interaction between evolution and the ability to teach oneself in self-taught neural networks outperform evolution and self-teaching alone. Expand
Designing neural networks through neuroevolution
TLDR
This Review looks at several key aspects of modern neuroevolution, including large-scale computing, the benefits of novelty and diversity, the power of indirect encoding, and the field’s contributions to meta-learning and architecture search. Expand
University of Groningen Evolving Plasticity for Autonomous Learning under Changing Environmental Conditions
A fundamental aspect of learning in biological neural networks (BNNs) is the plasticity property which allows them to modify their configurations during their lifetime. Hebbian learning is aExpand
Stable Lifelong Learning: Spiking neurons as a solution to instability in plastic neural networks
TLDR
This work demonstrates that utilizing plasticity together with ANNs leads to instability beyond the prespecified lifespan used during training, and presents a solution to this instability through the use of spiking neurons. Expand
The Evolution of Self-taught Neural Networks in a Multi-agent Environment
TLDR
Experimental results show that learning presents an effect in increasing the performance of the evolving multi-agent system, andications for future work on evolving neural networks are presented. Expand
Nurturing Promotes the Evolution of Generalized Supervised Learning
TLDR
It is found that nurturing promotes the evolution of generalized supervised learning in these environments and is able to increase the competitiveness of learning in an evolutionary environment by ameliorating the consequences of incorrect initial behavior. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 465 REFERENCES
On the Relationships between Generative Encodings, Regularity, and Learning Abilities when Evolving Plastic Artificial Neural Networks
TLDR
The results suggest that using a developmental encoding could improve the learning abilities of evolved, plastic neural networks, and reveal the consequence of the bias of developmental encodings towards regular structures. Expand
Evolving plastic neural networks with novelty search
TLDR
This article analyzes this inherent deceptiveness in a variety of different dynamic, reward-based learning tasks, and proposes a way to escape the deceptive trap of static policies based on the novelty search algorithm, which avoids deception entirely. Expand
Evolution of Cartesian Genetic Programs for Development of Learning Neural Architecture
TLDR
The goal of this paper is to use evolutionary approaches to find suitable computational functions that are analogous to natural sub-components of biological neurons and demonstrate that intelligent behavior can be produced as a result of this additional biological plausibility. Expand
A unified approach to evolving plasticity and neural geometry
TLDR
The most interesting aspect of this investigation is that the emergent neural structures are beginning to acquire more natural properties, which means that neuroevolution can begin to pose new problems and answer deeper questions about how brains evolved that are ultimately relevant to the field of AI as a whole. Expand
Differentiable plasticity: training plastic neural networks with backpropagation
TLDR
It is shown that plasticity, just like connection weights, can be optimized by gradient descent in large (millions of parameters) recurrent networks with Hebbian plastic connections, and it is concluded that differentiable plasticity may provide a powerful novel approach to the learning-to-learn problem. Expand
Indirectly Encoding Neural Plasticity as a Pattern of Local Rules
TLDR
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. Expand
In search of intelligence: evolving a developmental neuron capable of learning
TLDR
A neuro-inspired multi-chromosomal genotype for a single developmental neuron capable of learning and developing memory is proposed, evolved so that the phenotype which changes and develops during an agent's lifetime gives the agent the capacity for learning by experience. Expand
Learning to Adapt to Changing Environments in Evolving Neural Networks
TLDR
A genetic algorithm is used to simulate the evolution of a population of neural networks, each controlling the behavior of a small mobile robot that must explore efficiently an environment surrounded by walls, and found that evolved networks incorporate a genetically inherited predisposition to learn. Expand
Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies
New approaches to artificial intelligence spring from the idea that intelligence emerges as much from cells, bodies, and societies as it does from evolution, development, and learning. Traditionally,Expand
Using a map-based encoding to evolve plastic neural networks
TLDR
This work proposes to use a combination of Hebbian learning, neuro-modulation and a a generative map-based encoding on a problem from operant conditioning (a Skinner box), in which numerous different association rules can be learned. Expand
...
1
2
3
4
5
...