Training Deep Neural Networks with Constrained Learning Parameters

被引:0
作者
Date, Prasanna [1 ]
Carothers, Christopher D. [1 ]
Mitchell, John E. [2 ]
Hendler, James A. [1 ]
Magdon-Ismail, Malik [1 ]
机构
[1] Rensselaer Polytech Inst, Dept Comp Sci, Troy, NY 12180 USA
[2] Rensselaer Polytech Inst, Dept Math Sci, Troy, NY 12180 USA
来源
2020 INTERNATIONAL CONFERENCE ON REBOOTING COMPUTING (ICRC 2020) | 2020年
关键词
Deep Neural Networks; Training Algorithm; Deep Learning; Machine Learning; Artificial Intelligence; LOCAL SEARCH; OPTIMIZATION;
D O I
10.1109/ICRC2020.2020.00018
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Today's deep learning models are primarily trained on CPUs and GPUs. Although these models tend to have low error, they consume high power and utilize large amount of memory owing to double precision floating point learning parameters. Beyond the Moore's law, a significant portion of deep learning tasks would run on edge computing systems, which will form an indispensable part of the entire computation fabric. Subsequently, training deep learning models for such systems will have to be tailored and adopted to generate models that have the following desirable characteristics: low error, low memory, and low power. We believe that deep neural networks (DNNs), where learning parameters are constrained to have a set of finite discrete values, running on neuromorphic computing systems would be instrumental for intelligent edge computing systems having these desirable characteristics. To this extent, we propose the Combinatorial Neural Network Training Algorithm (CoNNTrA), that leverages a coordinate gradient descent-based approach for training deep learning models with finite discrete learning parameters. Next, we elaborate on the theoretical underpinnings and evaluate the computational complexity of CoNNTrA. As a proof of concept, we use CoNNTrA to train deep learning models with ternary learning parameters on the MNIST, Iris and ImageNet data sets and compare their performance to the same models trained using Backpropagation. We use following performance metrics for the comparison: (i) Training error; (ii) Validation error; (iii) Memory usage; and (iv) Training time. Our results indicate that CoNNTrA models use 32x less memory and have errors at par with the Backpropagation models.
引用
收藏
页码:107 / 115
页数:9
相关论文
共 32 条
  • [11] Hamilton Kathleen, 2020, ICONS 2020: International Conference on Neuromorphic Systems 2020, DOI 10.1145/3407197.3407219
  • [12] Hamilton Kathleen, 2020, ICONS 2020: International Conference on Neuromorphic Systems 2020, DOI 10.1145/3407197.3407199
  • [13] Hubara I, 2018, J MACH LEARN RES, V18
  • [14] Theory-Guided Data Science: A New Paradigm for Scientific Discovery from Data
    Karpatne, Anuj
    Atluri, Gowtham
    Faghmous, James H.
    Steinbach, Michael
    Banerjee, Arindam
    Ganguly, Auroop
    Shekhar, Shashi
    Samatova, Nagiza
    Kumar, Vipin
    [J]. IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2017, 29 (10) : 2318 - 2331
  • [15] Kay Bill, 2020, NICE '20: Proceedings of the Neuro-inspired Computational Elements Workshop, DOI 10.1145/3381755.3381762
  • [16] The unconstrained binary quadratic programming problem: a survey
    Kochenberger, Gary
    Hao, Jin-Kao
    Glover, Fred
    Lewis, Mark
    Lu, Zhipeng
    Wang, Haibo
    Wang, Yang
    [J]. JOURNAL OF COMBINATORIAL OPTIMIZATION, 2014, 28 (01) : 58 - 81
  • [17] ImageNet Classification with Deep Convolutional Neural Networks
    Krizhevsky, Alex
    Sutskever, Ilya
    Hinton, Geoffrey E.
    [J]. COMMUNICATIONS OF THE ACM, 2017, 60 (06) : 84 - 90
  • [18] Gradient-based learning applied to document recognition
    Lecun, Y
    Bottou, L
    Bengio, Y
    Haffner, P
    [J]. PROCEEDINGS OF THE IEEE, 1998, 86 (11) : 2278 - 2324
  • [19] Mailhiot C, 2018, ENERGY EFFICIENT EDG
  • [20] On the Prospects for a (Deep) Learning Health Care System
    Naylor, C. David
    [J]. JAMA-JOURNAL OF THE AMERICAN MEDICAL ASSOCIATION, 2018, 320 (11): : 1099 - 1100