Index
Symbols
χ squared, 25
#, 6
A
Activation function, 46
AdS/CFT correspondence, 34, 175
Akaike’s information criteria, 24
Anti-de Sitter (AdS) spacetime, 34, 175
Attention mechanism, 70
Attractor, 150, 161
B
Backpropagation method, 47, 49, 64
Bayes’ theorem, 29
Bias, 50
Binary classification, 36
Black hole, 179, 183
Black hole entropy, 192
Boltzmann constant, 54
Boltzmann distribution, 37
Boltzmann machine, 102, 104
Box-ball system, 72
Bra, 47, 49
Bracket, 54
C
Canonical distribution, 53
Cellular automaton, 74
Chaos, 74, 135, 150
Checkerboard artifact, 60
CIFAR-10, 18
Compactification, 174
Computationally universal, 63
Conditional probability, 28
Conformal dimension, 181
Contrastive divergence method, 107, 125
Convolution, 57
Convolutional neural network, 57
Coupling constant, 37, 58
Cross entropy, 39
Curse of dimensionality, 88
D
Data generation probability, 21
Deep convolutional generative adversarial net
(DCGAN), 60
Deep learning, 27, 51
Deep neural network, 45
Detailed balance, 92, 108
Differential equation, 147
Divergence, 22
E
Emergence, 182
Empirical error, 22
Empirical probability, 22
Energy, 160
Entropy, 3
Equation of motion, 179
Equipartition of energy, 54
Error function, 35, 39, 64, 125, 148
Expectation value, 26, 101
Exploding gradient, 66
© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2021
A. Tanaka et al., Deep Learning and Physics, Mathematical Physics Studies,
https://doi.org/10.1007/978-981-33-6108-9
205
Symbols
χ squared, 25
#, 6
A
Activation function, 46
AdS/CFT correspondence, 34, 175
Akaike’s information criteria, 24
Anti-de Sitter (AdS) spacetime, 34, 175
Attention mechanism, 70
Attractor, 150, 161
B
Backpropagation method, 47, 49, 64
Bayes’ theorem, 29
Bias, 50
Binary classification, 36
Black hole, 179, 183
Black hole entropy, 192
Boltzmann constant, 54
Boltzmann distribution, 37
Boltzmann machine, 102, 104
Box-ball system, 72
Bra, 47, 49
Bracket, 54
C
Canonical distribution, 53
Cellular automaton, 74
Chaos, 74, 135, 150
Checkerboard artifact, 60
CIFAR-10, 18
Compactification, 174
Computationally universal, 63
Conditional probability, 28
Conformal dimension, 181
Contrastive divergence method, 107, 125
Convolution, 57
Convolutional neural network, 57
Coupling constant, 37, 58
Cross entropy, 39
Curse of dimensionality, 88
D
Data generation probability, 21
Deep convolutional generative adversarial net
(DCGAN), 60
Deep learning, 27, 51
Deep neural network, 45
Detailed balance, 92, 108
Differential equation, 147
Divergence, 22
E
Emergence, 182
Empirical error, 22
Empirical probability, 22
Energy, 160
Entropy, 3
Equation of motion, 179
Equipartition of energy, 54
Error function, 35, 39, 64, 125, 148
Expectation value, 26, 101
Exploding gradient, 66
© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2021
A. Tanaka et al., Deep Learning and Physics, Mathematical Physics Studies,
https://doi.org/10.1007/978-981-33-6108-9
205