Sparse Compressed Spiking Neural Network Accelerator for Object Detection

Abstract

Spiking neural networks (SNNs), which are inspired by the human brain, have recently gained popularity due to their relatively simple and low-power hardware for transmitting binary spikes and highly sparse activation maps. However, because SNNs contain extra time dimension information, the SNN accelerator will require more buffers and take longer to infer, especially for the more difficult high-resolution object detection task. As a result, this paper proposes a sparse compressed spiking neural network accelerator that takes advantage of the high sparsity of activation maps and weights by utilizing the proposed gated one-to-all product for low power and highly parallel model execution. The experimental result of the neural network shows 71.5$\%$ mAP with mixed (1,3) time steps on the IVS 3cls dataset. The accelerator with the TSMC 28nm CMOS process can achieve 1024$\times$576@29 frames per second processing when running at 500MHz with 35.88TOPS/W energy efficiency and 1.05mJ energy consumption per frame.

arXiv comment11 pages, 18 figures, to be published in IEEE Transactions on Circuits and Systems--I: Regular Papers

References in corpus (5)

• Decoupled Weight Decay Regularization
• A scalable multi-core architecture with heterogeneous memory structures for Dynamic Neuromorphic Asynchronous Processors (DYNAPs)
• A 0.086-mm${}^2$ 12.7-pJ/SOP 64k-Synapse 256-Neuron Online-Learning Digital Spiking Neuromorphic Processor in 28nm CMOS
• Pruning of Deep Spiking Neural Networks through Gradient Rewiring
• VSA: Reconfigurable Vectorwise Spiking Neural Network Accelerator

Cited by in corpus (1)

• A 71.2-$\mu$W Speech Recognition Accelerator with Recurrent Spiking Neural Network