Minitaur, an Event-Driven FPGA-Based Spiking Network Accelerator

Current neural networks are accumulating accolades for their performance on a variety of real-world computational tasks including recognition, classification, regression, and prediction, yet there are few scalable architectures that have emerged to address the challenges posed by their computation. This paper introduces Minitaur, an event-driven neural network accelerator, which is designed for low power and high performance. As an field-programmable gate array-based system, it can be integrated into existing robotics or it can offload computationally expensive neural network tasks from the CPU. The version presented here implements a spiking deep network which achieves 19 million postsynaptic currents per second on 1.5 W of power and supports up to 65 K neurons per board. The system records 92% accuracy on the MNIST handwritten digit classification and 71% accuracy on the 20 newsgroups classification data set. Due to its event-driven nature, it allows for trading off between accuracy and latency.

[1]  Ken Lang,et al.  NewsWeeder: Learning to Filter Netnews , 1995, ICML.

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

[3]  T. Schoenauer,et al.  MASPINN: novel concepts for a neuroaccelerator for spiking neural networks , 1999, Other Conferences.

[4]  Ronan G. Reilly,et al.  Efficient event-driven simulation of spiking neural networks , 2002 .

[5]  Eugene M. Izhikevich,et al.  Simple model of spiking neurons , 2003, IEEE Trans. Neural Networks.

[6]  Simon J Thorpe,et al.  SpikeNET: an event-driven simulation package for modelling large networks of spiking neurons , 2003, Network.

[7]  Richard M. Fujimoto,et al.  Parallel event-driven neural network simulations using the Hodgkin-Huxley neuron model , 2005, Workshop on Principles of Advanced and Distributed Simulation (PADS'05).

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

[9]  T. Delbruck,et al.  A 128 128 120 dB 15 s Latency Asynchronous Temporal Contrast Vision Sensor , 2006 .

[10]  Nicolas Brunel,et al.  Lapicque’s 1907 paper: from frogs to integrate-and-fire , 2007, Biological Cybernetics.

[11]  Rodrigo Agís,et al.  Hardware event-driven simulation engine for spiking neural networks , 2007 .

[12]  Ammar Belatreche,et al.  Challenges for large-scale implementations of spiking neural networks on FPGAs , 2007, Neurocomputing.

[13]  Nicholas T. Carnevale,et al.  Simulation of networks of spiking neurons: A review of tools and strategies , 2006, Journal of Computational Neuroscience.

[14]  Tobi Delbrück,et al.  A 128$\times$ 128 120 dB 15 $\mu$s Latency Asynchronous Temporal Contrast Vision Sensor , 2008, IEEE Journal of Solid-State Circuits.

[15]  Seda Ogrenci Memik,et al.  Towards an “early neural circuit simulator”: A FPGA implementation of processing in the rat whisker system , 2008, 2008 International Conference on Field Programmable Logic and Applications.

[16]  Tobias Delbrück,et al.  Frame-free dynamic digital vision , 2008 .

[17]  Wayne Luk,et al.  FPGA Accelerated Simulation of Biologically Plausible Spiking Neural Networks , 2009, 2009 17th IEEE Symposium on Field Programmable Custom Computing Machines.

[18]  Simon R. Schultz,et al.  A parallel spiking neural network simulator , 2009, 2009 International Conference on Field-Programmable Technology.

[19]  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.

[20]  Indranil Saha,et al.  journal homepage: www.elsevier.com/locate/neucom , 2022 .

[21]  Luca Maria Gambardella,et al.  Deep, Big, Simple Neural Nets for Handwritten Digit Recognition , 2010, Neural Computation.

[22]  Shih-Chii Liu,et al.  Neuromorphic sensory systems , 2010, Current Opinion in Neurobiology.

[23]  Dong Yu,et al.  Conversational Speech Transcription Using Context-Dependent Deep Neural Networks , 2012, ICML.

[24]  Berin Martini,et al.  Large-Scale FPGA-based Convolutional Networks , 2011 .

[25]  Andrew S. Cassidy,et al.  Design of a one million neuron single FPGA neuromorphic system for real-time multimodal scene analysis , 2011, 2011 45th Annual Conference on Information Sciences and Systems.

[26]  Wayne Luk,et al.  A Large-Scale Spiking Neural Network Accelerator for FPGA Systems , 2012, ICANN.

[27]  Geoffrey E. Hinton,et al.  Acoustic Modeling Using Deep Belief Networks , 2012, IEEE Transactions on Audio, Speech, and Language Processing.

[28]  Tobi Delbruck,et al.  Real-time classification and sensor fusion with a spiking deep belief network , 2013, Front. Neurosci..