Evolutionary robotics: what, why, and where to

S Doncieux, N Bredeche, JB Mouret… - Frontiers in Robotics and …, 2015‏ - frontiersin.org
Evolutionary robotics applies the selection, variation, and heredity principles of natural
evolution to the design of robots with embodied intelligence. It can be considered as a …

Neural modularity helps organisms evolve to learn new skills without forgetting old skills

KO Ellefsen, JB Mouret, J Clune - PLoS computational biology, 2015‏ - journals.plos.org
A long-standing goal in artificial intelligence is creating agents that can learn a variety of
different skills for different problems. In the artificial intelligence subfield of neural networks …

Diffusion-based neuromodulation can eliminate catastrophic forgetting in simple neural networks

R Velez, J Clune - PloS one, 2017‏ - journals.plos.org
A long-term goal of AI is to produce agents that can learn a diversity of skills throughout their
lifetimes and continuously improve those skills via experience. A longstanding obstacle …

Artificial neurogenesis: An introduction and selective review

T Kowaliw, N Bredeche, S Chevallier… - … and Learning in Artificial …, 2014‏ - Springer
In this introduction and review—like in the book which follows—we explore the hypothesis
that adaptive growth is a means of producing brain-like machines. The emulation of neural …

Investigating the evolution of a neuroplasticity network for learning

L Wang, J Orchard - IEEE Transactions on Systems, Man, and …, 2017‏ - ieeexplore.ieee.org
The processes of evolution and learning interact. Learning is an evolved strategy that
improves fitness, especially in a world where some aspects cannot realistically be encoded …

On the relationships between generative encodings, regularity, and learning abilities when evolving plastic artificial neural networks

P Tonelli, JB Mouret - PloS one, 2013‏ - journals.plos.org
A major goal of bio-inspired artificial intelligence is to design artificial neural networks with
abilities that resemble those of animal nervous systems. It is commonly believed that two …

Artificial evolution of plastic neural networks: a few key concepts

JB Mouret, P Tonelli - … Machines: combining Development and Learning in …, 2014‏ - Springer
This chapter introduces a hierarchy of concepts to classify the goals and the methods used
in articles that mix neuro-evolution and synaptic plasticity. We propose definitions of …

Overcoming deception in evolution of cognitive behaviors

J Lehman, R Miikkulainen - Proceedings of the 2014 Annual Conference …, 2014‏ - dl.acm.org
When scaling neuroevolution to complex behaviors, cognitive capabilities such as learning,
communication, and memory become increasingly important. However, successfully …

Evolving autonomous learning in cognitive networks

L Sheneman, A Hintze - Scientific reports, 2017‏ - nature.com
There are two common approaches for optimizing the performance of a machine: genetic
algorithms and machine learning. A genetic algorithm is applied over many generations …

The evolution of a generalized neural learning rule

J Orchard, L Wang - 2016 International Joint Conference on …, 2016‏ - ieeexplore.ieee.org
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 …