Genetic Programming with Memory for Approximate Data Reconstruction

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F26%3A0193318" target="_blank" >RIV/00216305:26230/26:0193318 - isvavai.cz</a>

Result on the web

<a href="https://link.springer.com/chapter/10.1007/978-981-96-0077-9_10" target="_blank" >https://link.springer.com/chapter/10.1007/978-981-96-0077-9_10</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-981-96-0077-9_10" target="_blank" >10.1007/978-981-96-0077-9_10</a>

Result language

angličtina

Original language name

Genetic Programming with Memory for Approximate Data Reconstruction

Original language description

This chapter addresses the computation-memorization trade-offs in the context of genetic programming (GP). We introduce genetic programming with memory (GPM) in which GP evolves not only the expression but also the content of a small local memory to better approximate the original data set. In particular, we evolved expression-memory pairs that can serve as weight generators and thus approximate the weights associated with convolutional layers of some convolutional neural networks (CNNs). This is potentially interesting for the efficient implementations of hardware accelerators of CNNs in which memory access is significantly more energy-demanding than arithmetic operations. In our approach, most of the weights are approximated using an evolved expression; only some fraction of them must be read from memory. For example, if memory contains 10% of the original weights, the weight generator evolved for a convolutional layer can approximate the original weights such that the CNN utilizing the generated weights shows less than a 1% drop in the classification accuracy on the MNIST data set. The memory requirements are reduced 3.1x or 12.6x for 8-bit or 32-bit weights, respectively. Additional experiments conducted for more complex CNNs and challenging image classification benchmarks show various impacts of weights' approximation on classification accuracy.

Czech name

—

Czech description

—

Type

C - Chapter in a specialist book

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

<a href="/en/project/GA24-10990S" target="_blank" >GA24-10990S: Hardware-Aware Machine Learning: From Automated Design to Innovative and Explainable Solutions</a><br>

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year

2025

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Book/collection name

Genetic Programming Theory and Practice XXI

ISBN

978-981-9600-76-2

Number of pages of the result

20

Pages from-to

199-218

Number of pages of the book

417

Publisher name

Springer Nature Singapore

Place of publication

Singapore

UT code for WoS chapter

—