Cognitive computing systems: Algorithms and applications for networks of neurosynaptic cores

Marching along the DARPA SyNAPSE roadmap, IBM unveils a trilogy of innovations towards the TrueNorth cognitive computing system inspired by the brain's function and efficiency. The non-von Neumann nature of the TrueNorth architecture necessitates a novel approach to efficient system design. To this end, we have developed a set of abstractions, algorithms, and applications that are natively efficient for TrueNorth. First, we developed repeatedly-used abstractions that span neural codes (such as binary, rate, population, and time-to-spike), long-range connectivity, and short-range connectivity. Second, we implemented ten algorithms that include convolution networks, spectral content estimators, liquid state machines, restricted Boltzmann machines, hidden Markov models, looming detection, temporal pattern matching, and various classifiers. Third, we demonstrate seven applications that include speaker recognition, music composer recognition, digit recognition, sequence prediction, collision avoidance, optical flow, and eye detection. Our results showcase the parallelism, versatility, rich connectivity, spatio-temporality, and multi-modality of the TrueNorth architecture as well as compositionality of the corelet programming paradigm and the flexibility of the underlying neuron model.

[1]  T. Poggio,et al.  A parallel algorithm for real-time computation of optical flow , 1989, Nature.

[2]  Wulfram Gerstner,et al.  Spiking Neuron Models: Single Neurons, Populations, Plasticity , 2002 .

[3]  Marco Wiering,et al.  Democratic Liquid State Machines for Music Recognition , 2008, Speech, Audio, Image and Biomedical Signal Processing using Neural Networks.

[4]  Dharmendra S. Modha,et al.  Cognitive computing , 2011, Commun. ACM.

[5]  Andrew S. Cassidy,et al.  Building block of a programmable neuromorphic substrate: A digital neurosynaptic core , 2012, The 2012 International Joint Conference on Neural Networks (IJCNN).

[6]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[7]  Sridha Sridharan,et al.  Audio-visual speaker identification using the CUAVE database , 2005, AVSP.

[8]  Yong Liu,et al.  A 45nm CMOS neuromorphic chip with a scalable architecture for learning in networks of spiking neurons , 2011, 2011 IEEE Custom Integrated Circuits Conference (CICC).

[9]  Tobi Delbrück,et al.  A 128 X 128 120db 30mw asynchronous vision sensor that responds to relative intensity change , 2006, 2006 IEEE International Solid State Circuits Conference - Digest of Technical Papers.

[10]  Petri Toiviainen,et al.  MIDI toolbox : MATLAB tools for music research , 2004 .

[11]  E H Adelson,et al.  Spatiotemporal energy models for the perception of motion. , 1985, Journal of the Optical Society of America. A, Optics and image science.

[12]  Marco Wiering,et al.  Speech, Audio, Image and Biomedical Signal Processing using Neural Networks , 2008 .

[13]  Andrew S. Cassidy,et al.  Cognitive computing programming paradigm: A Corelet Language for composing networks of neurosynaptic cores , 2013, The 2013 International Joint Conference on Neural Networks (IJCNN).

[14]  Colin Norman.  2011 International Science & Engineering Visualization Challenge. , 2012, Science.

[15]  J.N. Gowdy,et al.  CUAVE: A new audio-visual database for multimodal human-computer interface research , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[16]  Carlos Hitoshi Morimoto,et al.  Pupil detection and tracking using multiple light sources , 2000, Image Vis. Comput..

[17]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[18]  Henry Markram,et al.  Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations , 2002, Neural Computation.

[19]  Lawrence D. Jackel,et al.  Backpropagation Applied to Handwritten Zip Code Recognition , 1989, Neural Computation.

[20]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[21]  Myron Flickner,et al.  Compass: A scalable simulator for an architecture for cognitive computing , 2012, 2012 International Conference for High Performance Computing, Networking, Storage and Analysis.

[22]  Colin Norman,et al.  2012 Visualization Challenge , 2013 .

[23]  Dharmendra S. Modha,et al.  A digital neurosynaptic core using embedded crossbar memory with 45pJ per spike in 45nm , 2011, 2011 IEEE Custom Integrated Circuits Conference (CICC).

[24]  D. Modha,et al.  Network architecture of the long-distance pathways in the macaque brain , 2010, Proceedings of the National Academy of Sciences.

[25]  Wolfgang Maass,et al.  Liquid State Machines: Motivation, Theory, and Applications , 2010 .

[26]  S. Bermudez i Badia,et al.  A collision avoidance model based on the Lobula giant movement detector (LGMD) neuron of the locust , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[27]  Shigang Yue,et al.  Collision detection in complex dynamic scenes using an LGMD-based visual neural network with feature enhancement , 2006, IEEE Transactions on Neural Networks.

[28]  Bhanu Prasad,et al.  Speech, Audio, Image and Biomedical Signal Processing using Neural Networks , 2008, Studies in Computational Intelligence.

[29]  Andrew S. Cassidy,et al.  Cognitive computing building block: A versatile and efficient digital neuron model for neurosynaptic cores , 2013, The 2013 International Joint Conference on Neural Networks (IJCNN).

[30]  Stefano Carpin,et al.  USARSim: a robot simulator for research and education , 2007, Proceedings 2007 IEEE International Conference on Robotics and Automation.

[31]  Tobi Delbrück,et al.  Event-based 64-channel binaural silicon cochlea with Q enhancement mechanisms , 2010, Proceedings of 2010 IEEE International Symposium on Circuits and Systems.

[32]  Frederick Jelinek,et al.  Statistical methods for speech recognition , 1997 .