2022
DOI: 10.21468/scipostphys.12.3.081
|View full text |Cite
|
Sign up to set email alerts
|

The edge of chaos: quantum field theory and deep neural networks

Abstract: We explicitly construct the quantum field theory corresponding to a general class of deep neural networks encompassing both recurrent and feedforward architectures. We first consider the mean-field theory (MFT) obtained as the leading saddlepoint in the action, and derive the condition for criticality via the largest Lyapunov exponent. We then compute the loop corrections to the correlation function in a perturbative expansion in the ratio of depth T to width N, and find a precise analogy with the well-studied… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

1
12
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
6
1

Relationship

0
7

Authors

Journals

citations
Cited by 14 publications
(13 citation statements)
references
References 45 publications
1
12
0
Order By: Relevance
“…In [76], [36] a completely different approach for the correspondence between Euclidean QFTs and NNs is presented. Starting with a stochastic differential equation, which plays the role of a master equation for the neural network, the authors construct an action and a path integral, which provides the QFT attached to the network.…”
Section: Discussionmentioning
confidence: 99%
See 1 more Smart Citation
“…In [76], [36] a completely different approach for the correspondence between Euclidean QFTs and NNs is presented. Starting with a stochastic differential equation, which plays the role of a master equation for the neural network, the authors construct an action and a path integral, which provides the QFT attached to the network.…”
Section: Discussionmentioning
confidence: 99%
“…The case in which the architecture is embedded in a stochastic differential equation or in a discrete mater equation has been studied intensively lately, see e.g. [9], [36], [40], see also [17], [21]. The p-adic counterpart of this correspondence is an open problem.…”
Section: Discussionmentioning
confidence: 99%
“…which is meant as a 2 × 2 tensor equation consisting of tensors with four time indices (see appendix A.5 for details). Due to the normalization W aux (0|C) = 0, given by ( 30) or (29), respectively, the Hessian has a zero in the upper left corner S…”
Section: Next-to-leading Order Correctionsmentioning
confidence: 99%
“…The Gaussian process thus has limited capability of quantifying the expressivity of neural networks in relation to the required resources, such as the number of trained weights. Studies on finite-size corrections beyond the n → ∞ limit are so far restricted to DNNs [17][18][19][20][21][22][23][24][25][26][27][28] (but see [29] for stationary continuous-time recurrent networks). Understanding the limits of the putative equivalence of DNNs and RNNs on the mean-field level requires a common theoretical basis for the two architectures that would extend to finite n and finite n .…”
Section: Introductionmentioning
confidence: 99%
“…In appropriate limits, these networks become Gaussian processes [13][14][15][16][17]. Such Gaussian processes are closely related to the situation when one wants to understand the ensemble of quantum fluctuations of scalar field theories as discussed in [18][19][20][21][22]. Related to our work, we utilise the same interpretation of a NN as a scalar field.…”
Section: Related Workmentioning
confidence: 99%