Clock Gating-Based Effectual Realization of Stochastic Hyperbolic Tangent Function for Deep Neural Hardware Accelerators

Abstract

Comprehensive neural network applications led to the customization of a scheme to accelerate the computation on ASIC implementation. Hence, the determination of activation function in a neural network is an indispensable requisite. However, the specific design architecture of an activation function in a digital network encounters several difficulties as these activation functions demand additional hardware resources due to their non-linearity. This paper proposed an efficient hyperbolic tangent (tanh) function, wholly based on stochastic Computing methodology. The Hyperbolic tangent implementation is backed by the clock gating technique to curtail the dynamic power dissipation. The results are derived by implementing two different clock gating techniques on the proposed hardware. In this work, the proposed clock gating-based stochastic design for the implementation of activation function is efficient in terms of performance parameters such as area, power, and delay with negligible accuracy loss. MNIST dataset has been used for checking accuracy on LeNeT benchmark architecture. Furthermore, post-synthesis results show that the proposed clock gating design area is reduced by ≈ 70.62 % , power is reduced by ≈ 58.19 % , and delay is reduced by ≈ 98.87 % compared to the state of the art. © 2023, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.