Fixed-Point Code Synthesis For Neural Networks

TL;DR

This paper presents a novel method to convert trained neural networks into fixed-point representations using linear programming, ensuring minimal accuracy loss and enabling efficient implementation in resource-constrained safety-critical systems.

Contribution

It introduces a systematic approach to optimize fixed-point formats for neural networks, maintaining accuracy while enabling integer-only computations.

Findings

The method preserves neural network accuracy within user-defined thresholds.

Experimental results demonstrate the efficiency and effectiveness of the fixed-point synthesis.

The approach ensures the fixed-point neural network behaves identically to the original floating-point network.

Abstract

Over the last few years, neural networks have started penetrating safety critical systems to take decisions in robots, rockets, autonomous driving car, etc. A problem is that these critical systems often have limited computing resources. Often, they use the fixed-point arithmetic for its many advantages (rapidity, compatibility with small memory devices.) In this article, a new technique is introduced to tune the formats (precision) of already trained neural networks using fixed-point arithmetic, which can be implemented using integer operations only. The new optimized neural network computes the output with fixed-point numbers without modifying the accuracy up to a threshold fixed by the user. A fixed-point code is synthesized for the new optimized neural network ensuring the respect of the threshold for any input vector belonging the range [xmin, xmax] determined during the analysis. From a technical point of view, we do a preliminary analysis of our floating neural network to determine the worst cases, then we generate a system of linear constraints among integer variables that we can solve by linear programming. The solution of this system is the new fixed-point format of each neuron. The experimental results obtained show the efficiency of our method which can ensure that the new fixed-point neural network has the same behavior as the initial floating-point neural network.