Exploring the hidden dimensions of an optical extreme learning machine

被引:3
|
作者
Silva, Duarte [1 ,2 ]
Ferreira, Tiago [1 ,2 ]
Moreira, Felipe C. [1 ,2 ]
Rosa, Carla C. [1 ,2 ]
Guerreiro, Ariel [1 ,2 ]
Silva, Nuno A. [1 ,2 ]
机构
[1] Univ Porto, Fac Ciencias, Dept Fis & Astron, Rua Campo Alegre S-N, P-4169007 Porto, Portugal
[2] INESC TEC, Ctr Appl Photon, Rua Campo Alegre 687, P-4169007 Porto, Portugal
关键词
Extreme Learning Machine; Optical Computing; Machine Learning; Optics;
D O I
10.1051/jeos/2023001
中图分类号
O43 [光学];
学科分类号
070207 ; 0803 ;
摘要
Extreme Learning Machines (ELMs) are a versatile Machine Learning (ML) algorithm that features as the main advantage the possibility of a seamless implementation with physical systems. Yet, despite the success of the physical implementations of ELMs, there is still a lack of fundamental understanding in regard to their optical implementations. In this context, this work makes use of an optical complex media and wavefront shaping techniques to implement a versatile optical ELM playground to gain a deeper insight into these machines. In particular, we present experimental evidences on the correlation between the effective dimensionality of the hidden space and its generalization capability, thus bringing the inner workings of optical ELMs under a new light and opening paths toward future technological implementations of similar principles.
引用
收藏
页码:436 / 444
页数:4
相关论文
共 50 条
  • [41] Learning to Rank with Extreme Learning Machine
    Zong, Weiwei
    Huang, Guang-Bin
    NEURAL PROCESSING LETTERS, 2014, 39 (02) : 155 - 166
  • [42] Learning to Rank with Extreme Learning Machine
    Weiwei Zong
    Guang-Bin Huang
    Neural Processing Letters, 2014, 39 : 155 - 166
  • [43] Exploring Hidden Dimensions in Parallelizing Convolutional Neural Networks
    Jia, Zhihao
    Lin, Sina
    Qi, Charles R.
    Aiken, Alex
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 80, 2018, 80
  • [44] Extreme Learning Machine Combining Hidden-Layer Feature Weighting and Batch Training for Classification
    Wu, Chao
    Sang, Yu
    Gao, Yakun
    NEURAL PROCESSING LETTERS, 2023, 55 (08) : 10951 - 10973
  • [45] Numerical Computation of Partial Differential Equations by Hidden-Layer Concatenated Extreme Learning Machine
    Naxian Ni
    Suchuan Dong
    Journal of Scientific Computing, 2023, 95
  • [46] Reduce Training Error of Extreme Learning Machine by Selecting Appropriate Hidden Layer Output Matrix
    Lv, Yang
    Li, Bang
    Yu, Jinghu
    Ding, Yiming
    JOURNAL OF SYSTEMS SCIENCE AND SYSTEMS ENGINEERING, 2021, 30 (05) : 552 - 571
  • [47] Extreme Learning Machine Combining Hidden-Layer Feature Weighting and Batch Training for Classification
    Chao Wu
    Yu Sang
    Yakun Gao
    Neural Processing Letters, 2023, 55 : 10951 - 10973
  • [48] Numerical Computation of Partial Differential Equations by Hidden-Layer Concatenated Extreme Learning Machine
    Ni, Naxian
    Dong, Suchuan
    JOURNAL OF SCIENTIFIC COMPUTING, 2023, 95 (02)
  • [49] AN IMPROVEMENT OF EXTREME LEARNING MACHINE FOR COMPACT SINGLE-HIDDEN-LAYER FEEDFORWARD NEURAL NETWORKS
    Huynh, Hieu Trung
    Won, Yonggwan
    Kim, Jung-Ja
    INTERNATIONAL JOURNAL OF NEURAL SYSTEMS, 2008, 18 (05) : 433 - 441
  • [50] TFFN: Two Hidden Layer Feed Forward Network using the randomness of Extreme Learning Machine
    Das Adhikari, Nimai Chand
    Alka, Arpana
    George, Raju K.
    PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON INTELLIGENT SUSTAINABLE SYSTEMS (ICISS 2017), 2017, : 852 - 857