Template based black-box optimization of dynamic neural fields

被引：6
|
作者：
Fix, Jeremy [1 ]
机构：
[1] UMI 2958 Georgia Tech CNRS, IMS, Supelec, F-57070 Metz, France
来源：
NEURAL NETWORKS | 2013年 / 46卷
关键词：
Dynamic neural fields; Optimization; Particle swarm optimization; Covariance Matrix Adaptation Evolution Strategy; CMA EVOLUTION STRATEGY; SELF-ORGANIZATION; SIGNALS; MODEL;
D O I：
10.1016/j.neunet.2013.04.008
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Due to their strong non-linear behavior, optimizing the parameters of dynamic neural fields is particularly challenging and often relies on expert knowledge and trial and error. In this paper, we study the ability of particle swarm optimization (PSO) and covariance matrix adaptation (CMA-ES) to solve this problem when scenarios specifying the input feeding the field and desired output profiles are provided. A set of spatial lower and upper bounds, called templates are introduced to define a set of desired output profiles. The usefulness of the method is illustrated on three classical scenarios of dynamic neural fields: competition, working memory and tracking. (C) 2013 Elsevier Ltd. All rights reserved.
引用
收藏
页码：40 / 49
页数：10
相关论文
共 50 条
  • [21] Are Humans Bayesian in the Optimization of Black-Box Functions?
    Candelieri, Antonio
    Perego, Riccardo
    Giordani, Ilaria
    Archetti, Francesco
    NUMERICAL COMPUTATIONS: THEORY AND ALGORITHMS, PT II, 2020, 11974 : 32 - 42
  • [22] Black-box structural optimization of a mechanical component
    Calvel, Sonia
    Mongeau, Marcel
    COMPUTERS & INDUSTRIAL ENGINEERING, 2007, 53 (03) : 514 - 530
  • [23] Towards a framework for black-box simulation optimization
    Olafsson, S
    Kim, J
    WSC'01: PROCEEDINGS OF THE 2001 WINTER SIMULATION CONFERENCE, VOLS 1 AND 2, 2001, : 300 - 306
  • [24] AutoZOOM: Autoencoder-Based Zeroth Order Optimization Method for Attacking Black-Box Neural Networks
    Tu, Chun-Chen
    Ting, Paishun
    Chen, Pin-Yu
    Liu, Sijia
    Zhang, Huan
    Yi, Jinfeng
    Hsieh, Cho-Jui
    Cheng, Shin-Ming
    THIRTY-THIRD AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FIRST INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / NINTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2019, : 742 - 749
  • [25] Google Vizier: A Service for Black-Box Optimization
    Golovin, Daniel
    Solnik, Benjamin
    Moitra, Subhodeep
    Kochanski, Greg
    Karro, John
    Sculley, D.
    KDD'17: PROCEEDINGS OF THE 23RD ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, 2017, : 1487 - 1496
  • [26] Combinatorial Black-Box Optimization with Expert Advice
    Dadkhahi, Hamid
    Shanmugam, Karthikeyan
    Rios, Jesus
    Das, Payel
    Hoffman, Samuel C.
    Loeffler, Troy David
    Sankaranarayanan, Subramanian
    KDD '20: PROCEEDINGS OF THE 26TH ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING, 2020, : 1918 - 1927
  • [27] Meta-Learning for Black-Box Optimization
    Vishnu, T. V.
    Malhotra, Pankaj
    Narwariya, Jyoti
    Vig, Lovekesh
    Shroff, Gautam
    MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES, ECML PKDD 2019, PT II, 2020, 11907 : 366 - 381
  • [28] A Black-Box Attack on Neural Networks Based on Swarm Evolutionary Algorithm
    Liu, Xiaolei
    Hu, Teng
    Ding, Kangyi
    Bai, Yang
    Niu, Weina
    Lu, Jiazhong
    INFORMATION SECURITY AND PRIVACY, ACISP 2020, 2020, 12248 : 268 - 284
  • [29] THE BLACK-BOX
    KYLE, SA
    NEW SCIENTIST, 1986, 110 (1512) : 61 - 61
  • [30] Population-Based Black-Box Optimization for Biological Sequence Design
    Angermueller, Christof
    Belanger, David
    Gane, Andreea
    Mariet, Zelda
    Dohan, David
    Murphy, Kevin
    Colwell, Lucy
    Sculley, D.
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 119, 2020, 119
12345