Stochastic-Based Convolutional Networks with Reconfigurable Logic Fabric
Authors:
- 8 September 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 713-718
Abstract
Convolutional neural network (CNN), well-known to be computationally intensive, is a fundamental algorithmic building block in many computer vision and artificial intelligence applications that follow the deep learning principle. This work presents a novel stochastic-based and scalable hardware architecture and circuit design that computes a convolutional neural network with FPGA. The key idea is to implement a multidimensional convolution accelerator that leverages the widely-used convolution theorem. Our approach has three advantages. First, it can achieve significantly lower algorithmic complexity for any given accuracy requirement. This computing complexity, when compared with that of conventional multiplier-based and FFT-based architectures, represents a significant performance improvement. Second, this proposed stochastic-based architecture is highly fault-tolerant because the information to be processed is encoded with a large ensemble of random samples. As such, the local perturbations of its computing accuracy will be dissipated globally, thus becoming inconsequential to the final overall results. Overall, being highly scalable and energy efficient, our stochastic-based convolutional neural network architecture is well-suited for a modular vision engine with the goal of performing real-time detection, recognition and segmentation of mega-pixel images, especially those perception-based computing tasks that are inherently fault-tolerant. We also present a performance comparison between FPGA implementations that use deterministic-based and Stochastic-based architectures.Keywords
This publication has 11 references indexed in Scilit:
- ShiDianNaoACM SIGARCH Computer Architecture News, 2015
- Spiking Deep Convolutional Neural Networks for Energy-Efficient Object RecognitionInternational Journal of Computer Vision, 2014
- Noise as a Resource for Computation and Learning in Networks of Spiking NeuronsProceedings of the IEEE, 2014
- Energy-efficient multiplier-less discrete convolver through probabilistic domain transformation2014
- Minimizing Computation in Convolutional Neural Networks2014
- Convolutional Neural Networks Applied to Human Face Classification2012
- Transforming Probabilities With Combinational LogicIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2011
- A dynamically configurable coprocessor for convolutional neural networksACM SIGARCH Computer Architecture News, 2010
- CNP: An FPGA-based processor for Convolutional Networks2009
- Face Detection Using GPU-Based Convolutional Neural Networks2009