Přístupnostní navigace
E-application
Search Search Close
Publication detail
JŮZA, T. SEKANINA, L.
Original Title
GPAM: Genetic Programming with Associative Memory
Type
conference paper
Language
English
Original Abstract
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.
Keywords
Genetic programming, Associative memory, Neural network, Weight compression, Symbolic regression
Authors
JŮZA, T.; SEKANINA, L.
Released
5. 4. 2023
Publisher
Springer Nature Switzerland AG
Location
Cham
ISBN
978-3-031-29572-0
Book
26th European Conference on Genetic Programming (EuroGP) Held as Part of EvoStar
Edition
LNCS
0302-9743
Periodical
Lecture Notes in Computer Science
Year of study
13986
Number
3
State
Federal Republic of Germany
Pages from
68
Pages to
83
Pages count
16
BibTex
@inproceedings{BUT185128, author="Tadeáš {Jůza} and Lukáš {Sekanina}", title="GPAM: Genetic Programming with Associative Memory", booktitle="26th European Conference on Genetic Programming (EuroGP) Held as Part of EvoStar", year="2023", series="LNCS", journal="Lecture Notes in Computer Science", volume="13986", number="3", pages="68--83", publisher="Springer Nature Switzerland AG", address="Cham", doi="10.1007/978-3-031-29573-7\{_}5", isbn="978-3-031-29572-0", issn="0302-9743" }