Evolving neural networks that suffer minimal catastrophic forgetting

被引：2

作者：

Seipone, T ^{[1
]}

Bullinaria, JA ^{[1
]}

机构：

[1] Univ Birmingham, Sch Comp Sci, Birmingham B15 2TT, W Midlands, England

来源：

MODELING LANGUAGE, COGNITION AND ACTION | 2005年 / 16卷

关键词：

D O I：

10.1142/9789812701886_0040

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Catastrophic forgetting is a well-known failing of many neural network systems whereby training on new patterns causes them to forget previously learned patterns. Humans have evolved mechanisms to minimize this problem, and in this paper we present our preliminary attempts to use simulated evolution to generate neural networks that suffer significantly less from catastrophic forgetting than traditionally formulated networks.

引用

页码：385 / 390

页数：6

共 50 条

[1] Overcoming catastrophic forgetting in neural networks
Kirkpatricka, James
Pascanu, Razvan
Rabinowitz, Neil
Veness, Joel
Desjardins, Guillaume
Rusu, Andrei A.
Milan, Kieran
Quan, John
Ramalho, Tiago
Grabska-Barwinska, Agnieszka
Hassabis, Demis
Clopath, Claudia
Kumaran, Dharshan
Hadsell, Raia
[J]. PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 2017, 114 (13) : 3521 - 3526
[2] Measuring Catastrophic Forgetting in Neural Networks
Kemker, Ronald
McClure, Marc
Abitino, Angelina
Hayes, Tyler L.
Kanan, Christopher
[J]. THIRTY-SECOND AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTIETH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / EIGHTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2018, : 3390 - 3398
[3] Overcoming Catastrophic Forgetting in Graph Neural Networks
Liu, Huihui
Yang, Yiding
Wang, Xinchao
[J]. THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2021, 35 : 8653 - 8661
[4] Unsupervised Learning to Overcome Catastrophic Forgetting in Neural Networks
Munoz-Martin, Irene
Bianchi, Stefano
Pedretti, Giacomo
Melnic, Octavian
Ambrogio, Stefano
Ielmini, Daniele
[J]. IEEE JOURNAL ON EXPLORATORY SOLID-STATE COMPUTATIONAL DEVICES AND CIRCUITS, 2019, 5 (01): : 58 - 66
[5] Adaptation of artificial neural networks avoiding catastrophic forgetting
Albesano, Dario
Gernello, Roberto
Laface, Pietro
Mana, Franco
Scanzio, Stefano
[J]. 2006 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORK PROCEEDINGS, VOLS 1-10, 2006, : 1554 - 1561
[6] Overcoming Catastrophic Forgetting in Graph Neural Networks with Experience Replay
Zhou, Fan
Cao, Chengtai
[J]. THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2021, 35 : 4714 - 4722
[7] Neuron Clustering for Mitigating Catastrophic Forgetting in Feedforward Neural Networks
Goodrich, Ben
Arel, Itamar
[J]. 2014 IEEE SYMPOSIUM ON COMPUTATIONAL INTELLIGENCE IN DYNAMIC AND UNCERTAIN ENVIRONMENTS (CIDUE), 2014, : 62 - 68
[8] Avoiding catastrophic forgetting by coupling two reverberating neural networks
Ans, B
Rousset, S
[J]. COMPTES RENDUS DE L ACADEMIE DES SCIENCES SERIE III-SCIENCES DE LA VIE-LIFE SCIENCES, 1997, 320 (12): : 989 - 997
[9] Unsupervised Neuron Selection for Mitigating Catastrophic Forgetting in Neural Networks
Goodrich, Ben
Arel, Itamar
[J]. 2014 IEEE 57TH INTERNATIONAL MIDWEST SYMPOSIUM ON CIRCUITS AND SYSTEMS (MWSCAS), 2014, : 997 - 1000
[10] Catastrophic forgetting in connectionist networks
French, RM
[J]. TRENDS IN COGNITIVE SCIENCES, 1999, 3 (04) : 128 - 135

← 1 2 3 4 5 →