GPAM: Genetic Programming with Associative Memory
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F23%3APU149355" target="_blank" >RIV/00216305:26230/23:PU149355 - isvavai.cz</a>
Result on the web
<a href="http://dx.doi.org/10.1007/978-3-031-29573-7_5" target="_blank" >http://dx.doi.org/10.1007/978-3-031-29573-7_5</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-3-031-29573-7_5" target="_blank" >10.1007/978-3-031-29573-7_5</a>
Alternative languages
Result language
angličtina
Original language name
GPAM: Genetic Programming with Associative Memory
Original language description
We focus on the evolutionary design of programs capable of capturing more randomness and outliers in the input data set than the standard genetic programming (GP)-based methods typically allow. We propose Genetic Programming with Associative Memory (GPAM) -- a GP-based system for symbolic regression which can utilize a small associative memory to store various data points to better approximate the original data set. The method is evaluated on five standard benchmarks in which a certain number of data points is replaced by randomly generated values. In another case study, GPAM is used as an on-chip generator capable of approximating the weights for a convolutional neural network (CNN) to reduce the access to an external weight memory. Using Cartesian genetic programming (CGP), we evolved expression-memory pairs that can generate weights of a single CNN layer. If the associative 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.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
<a href="/en/project/GA21-13001S" target="_blank" >GA21-13001S: Automated design of hardware accelerators for resource-aware machine learning</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2023
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
26th European Conference on Genetic Programming (EuroGP) Held as Part of EvoStar
ISBN
978-3-031-29572-0
ISSN
0302-9743
e-ISSN
—
Number of pages
16
Pages from-to
68-83
Publisher name
Springer Nature Switzerland AG
Place of publication
Cham
Event location
Brno
Event date
Apr 12, 2023
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000999086900005