An evolutionary optimization framework for neural networks and neuromorphic architectures

As new neural network and neuromorphic architectures are being developed, new training methods that operate within the constraints of the new architectures are required. Evolutionary optimization (EO) is a convenient training method for new architectures. In this work, we review a spiking neural network architecture and a neuromorphic architecture, and we describe an EO training framework for these architectures. We present the results of this training framework on four classification data sets and compare those results to other neural network and neuromorphic implementations. We also discuss how this EO framework may be extended to other architectures.

[1]  Manan Suri,et al.  Exploiting Intrinsic Variability of Filamentary Resistive Memory for Extreme Learning Machine Architectures , 2015, IEEE Transactions on Nanotechnology.

[2]  Michal Valko,et al.  Evolutionary Feature Selection for Spiking Neural Network Pattern Classifiers , 2005, 2005 portuguese conference on artificial intelligence.

[3]  Sam Kwong,et al.  Genetic structure for NN topology and weights optimization , 1995 .

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

[5]  Risto Miikkulainen,et al.  Efficient Non-linear Control Through Neuroevolution , 2006, ECML.

[6]  Risto Miikkulainen,et al.  Efficient Reinforcement Learning through Symbiotic Evolution , 2004 .

[7]  Simei Gomes Wysoski,et al.  Fast and adaptive network of spiking neurons for multi-view visual pattern recognition , 2008, Neurocomputing.

[8]  Panos A. Ligomenides,et al.  GANNET: a genetic algorithm for searching topology and weight spaces in neural network design. The first step in finding a neural network solution , 1993 .

[9]  Vittorio Maniezzo,et al.  Genetic evolution of the topology and weight distribution of neural networks , 1994, IEEE Trans. Neural Networks.

[10]  Avinoam Kolodny,et al.  Memristor-Based Multilayer Neural Networks With Online Gradient Descent Training , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[11]  Jianguo Xin,et al.  Supervised learning with spiking neural networks , 2001, IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Cat. No.01CH37222).

[12]  Roberto Antonio Vázquez.  Pattern Recognition Using Spiking Neurons and Firing Rates , 2010, IBERAMIA.

[13]  László Bakó,et al.  Real-time classification of datasets with hardware embedded neuromorphic neural networks , 2010, Briefings Bioinform..

[14]  David B. Fogel,et al.  Evolving Neural Control Systems , 1995, IEEE Expert.

[15]  Roberto Antonio Vázquez,et al.  Integrate and Fire neurons and their application in pattern recognition , 2010, 2010 7th International Conference on Electrical Engineering Computing Science and Automatic Control.

[16]  Catherine D. Schuman,et al.  Dynamic adaptive neural network arrays: a neuromorphic architecture , 2015, MLHPC@SC.

[17]  Xin Yao,et al.  A new evolutionary system for evolving artificial neural networks , 1997, IEEE Trans. Neural Networks.

[18]  A. P. Wieland,et al.  Evolving neural network controllers for unstable systems , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[19]  Andrew S. Cassidy,et al.  A million spiking-neuron integrated circuit with a scalable communication network and interface , 2014, Science.

[20]  Risto Miikkulainen,et al.  Accelerated Neural Evolution through Cooperatively Coevolved Synapses , 2008, J. Mach. Learn. Res..

[21]  Lawrence Davis,et al.  Training Feedforward Neural Networks Using Genetic Algorithms , 1989, IJCAI.

[22]  Hani Hagras,et al.  Evolving spiking neural network controllers for autonomous robots , 2004, IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004.

[23]  Risto Miikkulainen,et al.  2-D Pole Balancing with Recurrent Evolutionary Networks , 1998 .

[24]  Johannes Schemmel,et al.  Six Networks on a Universal Neuromorphic Computing Substrate , 2012, Front. Neurosci..

[25]  Catherine D. Schuman.  Neuroscience-Inspired Dynamic Architectures , 2015 .

[26]  Hojjat Adeli,et al.  A new supervised learning algorithm for multiple spiking neural networks with application in epilepsy and seizure detection , 2009, Neural Networks.

[27]  D. R. McGregor,et al.  Designing application-specific neural networks using the structured genetic algorithm , 1992, [Proceedings] COGANN-92: International Workshop on Combinations of Genetic Algorithms and Neural Networks.

[28]  Sander M. Bohte,et al.  Error-backpropagation in temporally encoded networks of spiking neurons , 2000, Neurocomputing.

[29]  Catherine D. Schuman,et al.  Variable structure dynamic artificial neural networks , 2013, BICA 2013.

[30]  Roberto Antonio Vázquez,et al.  Training spiking neural models using cuckoo search algorithm , 2011, 2011 IEEE Congress of Evolutionary Computation (CEC).

[31]  Olivier Temam,et al.  A defect-tolerant accelerator for emerging high-performance applications , 2012, 2012 39th Annual International Symposium on Computer Architecture (ISCA).

[32]  Liam McDaid,et al.  Hardware spiking neural network prototyping and application , 2011, Genetic Programming and Evolvable Machines.

[33]  PoliRiccardo,et al.  Evolving the Topology and the Weights of Neural Networks Using a Dual Representation , 1998 .

[34]  François W. Primeau,et al.  A million spiking-neuron integrated circuit with a scalable communication network and interface , 2014 .

[35]  Muhaini Othman,et al.  Evolving spiking neural networks for personalised modelling, classification and prediction of spatio-temporal patterns with a case study on stroke , 2014, Neurocomputing.

[36]  David White,et al.  GANNet: A Genetic Algorithm for Optimizing Topology and Weights in Neural Network Design , 1993, IWANN.

[37]  Catherine D. Schuman,et al.  Dynamic Artificial Neural Networks with Affective Systems , 2013, PloS one.

[38]  Jim D. Garside,et al.  Overview of the SpiNNaker System Architecture , 2013, IEEE Transactions on Computers.

[39]  Yoshua Bengio,et al.  Learning long-term dependencies with gradient descent is difficult , 1994, IEEE Trans. Neural Networks.

[40]  César Hervás-Martínez,et al.  An alternative approach for neural network evolution with a genetic algorithm: Crossover by combinatorial optimization , 2006, Neural Networks.

[41]  Christian Igel,et al.  Neuroevolution for reinforcement learning using evolution strategies , 2003, The 2003 Congress on Evolutionary Computation, 2003. CEC '03..

[42]  Bernhard Sendhoff,et al.  Evolutionary Multi-objective Optimization of Spiking Neural Networks , 2007, ICANN.

[43]  Michael Schmitt,et al.  Unsupervised learning and self-organization in networks of spiking neurons , 2001 .

[44]  Tarek M. Taha,et al.  Enabling back propagation training of memristor crossbar neuromorphic processors , 2014, 2014 International Joint Conference on Neural Networks (IJCNN).

[45]  Kea-Tiong Tang,et al.  Hardware Friendly Probabilistic Spiking Neural Network With Long-Term and Short-Term Plasticity , 2013, IEEE Transactions on Neural Networks and Learning Systems.

[46]  Hieu Tat Nguyen,et al.  A gradient descent rule for spiking neurons emitting multiple spikes , 2005, Inf. Process. Lett..

[47]  Xin YaoComputational.  A Population-Based Learning Algorithm Which Learns BothArchitectures and Weights of Neural Networks , 1996 .

[48]  Rodrigo Alvarez-Icaza,et al.  Neurogrid: A Mixed-Analog-Digital Multichip System for Large-Scale Neural Simulations , 2014, Proceedings of the IEEE.

[49]  Ammar Belatreche,et al.  Advances in Design and Application of Spiking Neural Networks , 2006, Soft Comput..

[50]  Hussein A. Abbass,et al.  An evolutionary artificial neural networks approach for breast cancer diagnosis , 2002, Artif. Intell. Medicine.

[51]  Enrique Alba,et al.  Training Neural Networks with GA Hybrid Algorithms , 2004, GECCO.

[52]  Hak-Keung Lam,et al.  Tuning of the structure and parameters of a neural network using an improved genetic algorithm , 2003, IEEE Trans. Neural Networks.

[53]  Shiro Usui,et al.  Mutation-based genetic neural network , 2005, IEEE Transactions on Neural Networks.

[54]  Peter J. Angeline,et al.  An evolutionary algorithm that constructs recurrent neural networks , 1994, IEEE Trans. Neural Networks.

[55]  V.P. Plagianakos,et al.  Spiking neural network training using evolutionary algorithms , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[56]  Mikko H. Lipasti,et al.  BenchNN: On the broad potential application scope of hardware neural network accelerators , 2012, 2012 IEEE International Symposium on Workload Characterization (IISWC).

[57]  Dario Floreano,et al.  Evolution of Spiking Neural Controllers for Autonomous Vision-Based Robots , 2001, EvoRobots.

[58]  Linda Bushnell,et al.  Spike-Timing Error Backpropagation in Theta Neuron Networks , 2009, Neural Computation.

[59]  Gerald Sommer,et al.  Evolutionary reinforcement learning of artificial neural networks , 2007, Int. J. Hybrid Intell. Syst..

[60]  X. Yao.  Evolving Artificial Neural Networks , 1999 .

[61]  Catherine D. Schuman,et al.  Dynamic Adaptive Neural Network Array , 2014, UCNC.

[62]  Catherine D. Schuman,et al.  Neuroscience-inspired inspired dynamic architectures , 2014, Proceedings of the 2014 Biomedical Sciences and Engineering Conference.

[63]  A. Selverston,et al.  Dynamical principles in neuroscience , 2006 .

[64]  Risto Miikkulainen,et al.  Evolving neural networks , 2008, GECCO '08.

[65]  Patrick P. K. Chan,et al.  MLPNN Training via a Multiobjective Optimization of Training Error and Stochastic Sensitivity , 2016, IEEE Transactions on Neural Networks and Learning Systems.

[66]  Xin Yao,et al.  Evolving artificial neural network ensembles , 2008, IEEE Computational Intelligence Magazine.

[67]  D B Fogel,et al.  Evolving neural networks for detecting breast cancer. , 1995, Cancer letters.

[68]  Jonathan E. Fieldsend,et al.  Pareto evolutionary neural networks , 2005, IEEE Transactions on Neural Networks.

[69]  J. David Schaffer,et al.  Evolving spiking neural networks for robot control , 2011, Complex Adaptive Systems.

[70]  Catherine D. Schuman,et al.  Spatiotemporal Classification Using Neuroscience-Inspired Dynamic Architectures , 2014, BICA.