Genetic Programming with Transformer-Based Mutation for Approximate Circuit Design

TL;DR

This paper introduces a transformer-based mutation operator for Cartesian genetic programming to improve the automated design of approximate arithmetic circuits, achieving better trade-offs than existing solutions.

Contribution

It presents a novel transformer-based mutation method and a hybrid scheme for CGP, enhancing the evolutionary design of approximate circuits with improved performance.

Findings

Transformer-based mutation outperforms standard mutation in circuit design.

Hybrid scheme prevents stagnation in the evolutionary process.

Achieves better error-performance trade-offs than state-of-the-art designs.

Abstract

A recent trend is to leverage machine learning models to improve the evolutionary design and optimization process. We propose a novel transformer-based mutation operator for Cartesian genetic programming (CGP) for the automated design of approximate arithmetic circuits. We introduce a hybrid scheme for CGP in which the proposed mutation operator is switched with the standard mutation operator to prevent stagnation of the circuit approximation process. We also develop a new training scheme for the underlying transformer that utilizes training vectors composed of thousands of CGP chromosomes representing various approximate multipliers. For several target error constraints, the approximate multipliers evolved with CGP utilizing the transformer-based mutation achieve better trade-offs than the highly optimized designs available in the state-of-the-art EvoApproxLib library of approximate circuits. Although both training and evolutionary processes are computationally demanding, they appear to be necessary steps for improving existing approximate circuits and producing new, potentially patentable circuit designs.