Late Breaking Results: Conversion of Neural Networks into Logic Flows for Edge Computing

TL;DR

This paper introduces a method to convert neural networks into logic flows, enabling more efficient execution on CPUs in resource-constrained edge devices, reducing latency without accuracy loss.

Contribution

It presents a novel approach to transform neural networks into logic flows via decision trees, optimizing their execution on CPUs for edge computing.

Findings

Latency reduced by up to 14.9% on RISC-V CPU

No accuracy degradation observed

Open source implementation available

Abstract

Neural networks have been successfully applied in various resource-constrained edge devices, where usually central processing units (CPUs) instead of graphics processing units exist due to limited power availability. State-of-the-art research still focuses on efficiently executing enormous numbers of multiply-accumulate (MAC) operations. However, CPUs themselves are not good at executing such mathematical operations on a large scale, since they are more suited to execute control flow logic, i.e., computer algorithms. To enhance the computation efficiency of neural networks on CPUs, in this paper, we propose to convert them into logic flows for execution. Specifically, neural networks are first converted into equivalent decision trees, from which decision paths with constant leaves are then selected and compressed into logic flows. Such logic flows consist of if and else structures and a reduced number of MAC operations. Experimental results demonstrate that the latency can be reduced by up to 14.9 % on a simulated RISC-V CPU without any accuracy degradation. The code is open source at https://github.com/TUDa-HWAI/NN2Logic