Learning From Pseudo-Randomness Will an Artificial Neural Network-Does God Play Pseudo-Dice?

被引:20
作者
Fan, Fenglei [1 ]
Wang, Ge [1 ]
机构
[1] Rensselaer Polytech Inst, Biomed Imaging Ctr, BME CBIS, Troy, NY 12180 USA
来源
IEEE ACCESS | 2018年 / 6卷
关键词
Pseudo-random number; artificial neural network (ANN); prediction; quantum mechanics; CHAOTIC TIME-SERIES; PREDICTION;
D O I
10.1109/ACCESS.2018.2826448
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Inspired by the fact that the neural network, as the mainstream method for machine learning, has brought successes in many application areas, here we propose to use this approach for decoding hidden correlation among pseudo-random data and predicting events accordingly. With a simple neural network structure and a typical training procedure, we demonstrate the learning and prediction power of the neural network in pseudo-random environments. Finally, we postulate that the high sensitivity and efficiency of the neural network may allow learning on a low-dimensional manifold in a high-dimensional space of pseudorandom events and critically test, if there could be any fundamental difference between quantum randomness and pseudo randomness, which is equivalent to the classic question: Does God play dice? (Note that this analogy was first made by Einstein in his famous quotation "God does not play dice with the universe". He believed in laws of nature, and hence, the meaning of God in this context was some mechanism responsible for the ways by which the universe evolves.)
引用
收藏
页码:22987 / 22992
页数:6
相关论文
共 23 条
[1]  
Agafonov V. N., 1968, SOV MATH DOKL, V9, P5
[2]  
[Anonymous], 2017, LEARN LEARNED EXPERT
[4]   On the random character of fundamental constant expansions [J].
Bailey, DH ;
Crandall, RE .
EXPERIMENTAL MATHEMATICS, 2001, 10 (02) :175-190
[5]   Bypassing the Kohn-Sham equations with machine learning [J].
Brockherde, Felix ;
Vogt, Leslie ;
Li, Li ;
Tuckerman, Mark E. ;
Burke, Kieron ;
Mueller, Klaus-Robert .
NATURE COMMUNICATIONS, 2017, 8
[6]   Predicting chaotic time series with wavelet networks [J].
1600, Elsevier Science B.V., Amsterdam, Netherlands (85) :1-2
[7]   NOTE ON NORMAL DECIMALS [J].
DAVENPORT, H ;
ERDOS, P .
CANADIAN JOURNAL OF MATHEMATICS-JOURNAL CANADIEN DE MATHEMATIQUES, 1952, 4 (01) :58-63
[8]   A new type of neurons for machine learning [J].
Fan, Fenglei ;
Cong, Wenxiang ;
Wang, Ge .
INTERNATIONAL JOURNAL FOR NUMERICAL METHODS IN BIOMEDICAL ENGINEERING, 2018, 34 (02)
[9]   Generative Adversarial Networks [J].
Goodfellow, Ian ;
Pouget-Abadie, Jean ;
Mirza, Mehdi ;
Xu, Bing ;
Warde-Farley, David ;
Ozair, Sherjil ;
Courville, Aaron ;
Bengio, Yoshua .
COMMUNICATIONS OF THE ACM, 2020, 63 (11) :139-144
[10]   Prediction of chaotic time series based on the recurrent predictor neural network [J].
Han, M ;
Xi, JH ;
Xu, SG ;
Yin, FL .
IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2004, 52 (12) :3409-3416