The effects of morphology and fitness on catastrophic interference

Catastrophic interference occurs when an agent improves in one training instance but becomes worse in other instances. Many methods intended to combat interference have been reported in the literat...

[1]  Helmut Hauser,et al.  Towards a theoretical foundation for morphological computation with compliant bodies , 2011, Biological Cybernetics.

[2]  Inman Harvey,et al.  Evolutionary robotics: the Sussex approach , 1997, Robotics Auton. Syst..

[3]  Francesco Mondada,et al.  Automatic creation of an autonomous agent: genetic evolution of a neural-network driven robot , 1994 .

[4]  Josh C. Bongard,et al.  Evolutionary robotics , 2013, CACM.

[5]  Leonardo Vanneschi,et al.  A survey of semantic methods in genetic programming , 2014, Genetic Programming and Evolvable Machines.

[6]  Hod Lipson,et al.  Unshackling evolution: evolving soft robots with multiple materials and a powerful generative encoding , 2013, GECCO '13.

[7]  Kyu-Jin Cho,et al.  Wheel Transformer: A Wheel-Leg Hybrid Robot With Passive Transformable Wheels , 2014, IEEE Transactions on Robotics.

[8]  Risto Miikkulainen,et al.  Evolving Neural Networks through Augmenting Topologies , 2002, Evolutionary Computation.

[9]  Razvan Pascanu,et al.  Overcoming catastrophic forgetting in neural networks , 2016, Proceedings of the National Academy of Sciences.

[10]  Hod Lipson,et al.  ON THE ORIGIN OF MODULAR VARIATION , 2002, Evolution; international journal of organic evolution.

[11]  L. Darrell Whitley,et al.  Adding Learning to the Cellular Development of Neural Networks: Evolution and the Baldwin Effect , 1993, Evolutionary Computation.

[12]  Jeff Clune,et al.  Diffusion-based neuromodulation can eliminate catastrophic forgetting in simple neural networks , 2017, PloS one.

[13]  Josh Bongard,et al.  Morphological change in machines accelerates the evolution of robust behavior , 2011, Proceedings of the National Academy of Sciences.

[14]  Karl Sims,et al.  Evolving 3d morphology and behavior by competition , 1994 .

[15]  Norhayati Daut,et al.  Fixed vs. self-adaptive crossover first differential evolution , 2016 .

[16]  Razvan Pascanu,et al.  Progressive Neural Networks , 2016, ArXiv.

[17]  Michael McCloskey,et al.  Catastrophic Interference in Connectionist Networks: The Sequential Learning Problem , 1989 .

[18]  Josh C. Bongard,et al.  Evolving Robot Morphology Facilitates the Evolution of Neural Modularity and Evolvability , 2015, GECCO.

[19]  Josh C. Bongard,et al.  Choice of robot morphology can prohibit modular control and disrupt evolution , 2017, ECAL.

[20]  Chrisantha Fernando,et al.  PathNet: Evolution Channels Gradient Descent in Super Neural Networks , 2017, ArXiv.

[21]  Kenneth O. Stanley,et al.  Safe mutations for deep and recurrent neural networks through output gradients , 2017, GECCO.

[22]  Andreas Wagner,et al.  Specialization Can Drive the Evolution of Modularity , 2010, PLoS Comput. Biol..

[23]  Krzysztof Walas,et al.  Affordable Multi-legged Robots for Research and STEM Education: A Case Study of Design and Technological Aspects , 2015, Progress in Automation, Robotics and Measuring Techniques.

[24]  Byoung-Tak Zhang,et al.  Dual-Memory Deep Learning Architectures for Lifelong Learning of Everyday Human Behaviors , 2016, IJCAI.

[25]  Sangram Ganguly,et al.  Semantic Forward Propagation for Symbolic Regression , 2016, PPSN.

[26]  Hod Lipson,et al.  Resilient Machines Through Continuous Self-Modeling , 2006, Science.

[27]  Roger D. Quinn,et al.  Comparing cockroach and Whegs robot body motions , 2004, IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004.

[28]  Geoffrey E. Hinton,et al.  Dynamic Routing Between Capsules , 2017, NIPS.

[29]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[30]  U. Alon,et al.  Spontaneous evolution of modularity and network motifs. , 2005, Proceedings of the National Academy of Sciences of the United States of America.

[31]  R. Pfeifer,et al.  Repeated structure and dissociation of genotypic and phenotypic complexity in artificial ontogeny , 2001 .

[32]  Elliot Meyerson,et al.  Evolving Deep Neural Networks , 2017, Artificial Intelligence in the Age of Neural Networks and Brain Computing.

[33]  Josh C. Bongard,et al.  How morphological development can guide evolution , 2017, Scientific Reports.

[34]  Jean-Baptiste Mouret,et al.  Neural Modularity Helps Organisms Evolve to Learn New Skills without Forgetting Old Skills , 2015, PLoS Comput. Biol..

[35]  R. French.  Catastrophic Forgetting in Connectionist Networks , 2006 .

[36]  Antoine Cully,et al.  Design of a Wheel-Legged Hexapod Robot for Creative Adaptation , 2014 .

[37]  Hod Lipson,et al.  Aracna: An Open-Source Quadruped Platform for Evolutionary Robotics , 2012, ALIFE.

[38]  Yoshua Bengio,et al.  An Empirical Investigation of Catastrophic Forgeting in Gradient-Based Neural Networks , 2013, ICLR.

[39]  Hod Lipson,et al.  The evolutionary origins of modularity , 2012, Proceedings of the Royal Society B: Biological Sciences.

[40]  Duc-Cuong Dang,et al.  Self-adaptation of Mutation Rates in Non-elitist Populations , 2016, PPSN.