English
Related papers

Related papers: Tensor Programs III: Neural Matrix Laws

200 papers

We applied physics-informed neural networks to solve the constitutive relations for nonlinear, path-dependent material behavior. As a result, the trained network not only satisfies all thermodynamic constraints but also instantly provides…

Computational Engineering, Finance, and Science · Computer Science 2023-09-07 Shahed Rezaei , Ahmad Moeineddin , Ali Harandi

Approximate Message Passing (AMP) algorithms provide a valuable tool for studying mean-field approximations and dynamics in a variety of applications. Although these algorithms are often first derived for matrices having independent…

Probability · Mathematics 2024-09-10 Tianhao Wang , Xinyi Zhong , Zhou Fan

We prove the converse of the universal approximation theorem, i.e. a neural network (NN) encoding theorem which shows that for every stably converged NN of continuous activation functions, its weight matrix actually encodes a continuous…

Machine Learning · Computer Science 2023-09-13 Ng Shyh-Chang , A-Li Luo , Bo Qiu

The interpretability of neural networks (NNs) is a challenging but essential topic for transparency in the decision-making process using machine learning. One of the reasons for the lack of interpretability is random weight initialization,…

Machine Learning · Computer Science 2021-03-01 Shohei Kubota , Hideaki Hayashi , Tomohiro Hayase , Seiichi Uchida

We propose an algorithm for inexpensive gradient-based hyperparameter optimization that combines the implicit function theorem (IFT) with efficient inverse Hessian approximations. We present results about the relationship between the IFT…

Machine Learning · Computer Science 2019-11-11 Jonathan Lorraine , Paul Vicol , David Duvenaud

This work demonstrates how increasing the number of neurons in a network without increasing its number of non-zero parameters improves performance. We show that this gain corresponds with a decrease in interference between multiple features…

Machine Learning · Computer Science 2025-10-07 Linghao Kong , Inimai Subramanian , Yonadav Shavit , Micah Adler , Dan Alistarh , Nir Shavit

We develop a diagrammatic approach to effective field theories (EFTs) corresponding to deep neural networks at initialization, which dramatically simplifies computations of finite-width corrections to neuron statistics. The structures of…

High Energy Physics - Theory · Physics 2023-05-12 Ian Banta , Tianji Cai , Nathaniel Craig , Zhengkang Zhang

On the basis of the general form for the energy needed to adapt the connection strengths of a network in which learning takes place, a local learning rule is found for the changes of the weights. This biologically realizable learning rule…

Disordered Systems and Neural Networks · Physics 2009-10-31 M. Heerema , W. A. van Leeuwen

We study the asymptotic law of a network of interacting neurons when the number of neurons becomes infinite. Given a completely connected network of firing rate neurons in which the synaptic weights are Gaussian correlated random variables,…

Probability · Mathematics 2013-06-03 Olivier Faugeras , James MacLaurin

Multiplications are responsible for most of the computational cost involved in neural network training and inference. Recent research has thus looked for ways to reduce the cost associated with them. Inspired by Mogami (2020), we replace…

Machine Learning · Computer Science 2023-10-26 Atli Kosson , Martin Jaggi

Attractor dynamics are a hallmark of many complex systems, including the brain. Understanding how such self-organizing dynamics emerge from first principles is crucial for advancing our understanding of neuronal computations and the design…

Neurons and Cognition · Quantitative Biology 2026-05-22 Tamas Spisak , Karl Friston

We propose a new algorithm for training neural networks with binary activations and multi-level weights, which enables efficient processing-in-memory circuits with embedded nonvolatile memories (eNVM). Binary activations obviate costly DACs…

Machine Learning · Computer Science 2020-10-13 Siming Ma , David Brooks , Gu-Yeon Wei

At initialization, artificial neural networks (ANNs) are equivalent to Gaussian processes in the infinite-width limit, thus connecting them to kernel methods. We prove that the evolution of an ANN during training can also be described by a…

Machine Learning · Computer Science 2020-02-11 Arthur Jacot , Franck Gabriel , Clément Hongler

We construct a cellular sheaf from any feedforward ReLU neural network by placing one vertex for each intermediate quantity in the forward pass and encoding each computational step - affine transformation, activation, output - as a…

Algebraic Topology · Mathematics 2026-03-26 Vicente Bosca , Robert Ghrist

Parameter estimation in empirical fields is usually undertaken using parametric models, and such models readily facilitate statistical inference. Unfortunately, they are unlikely to be sufficiently flexible to be able to adequately model…

Machine Learning · Computer Science 2022-06-13 Matthew J. Vowels , Sina Akbari , Necati Cihan Camgoz , Richard Bowden

We show how any system with morphological degrees of freedom and locally limited free energy will, under the constraints of the free energy principle, evolve toward a neuromorphic morphology that supports hierarchical computations in which…

Quantum Physics · Physics 2023-02-28 Chris Fields , Karl Friston , James F. Glazebrook , Michael Levin , Antonino Marcianò

This thesis focuses on three fundamental aspects of biological systems; namely, entropy production, Bayesian mechanics, and the free-energy principle. The contributions are threefold: 1) We compute the entropy production for a greater class…

Mathematical Physics · Physics 2024-10-16 Lancelot Da Costa

To adopt neural networks in safety critical domains, knowing whether we can trust their predictions is crucial. Bayesian neural networks (BNNs) provide uncertainty estimates by averaging predictions with respect to the posterior weight…

Machine Learning · Computer Science 2021-03-17 Jannik Schmitt , Stefan Roth

Animals survive in dynamic environments changing at arbitrary timescales, but such data distribution shifts are a challenge to neural networks. To adapt to change, neural systems may change a large number of parameters, which is a slow…

Machine Learning · Computer Science 2025-01-17 Kai Sandbrink , Jan P. Bauer , Alexandra M. Proca , Andrew M. Saxe , Christopher Summerfield , Ali Hummos

We introduce Neural Tensor Network States ($\nu$TNS), a variational many-body wave-function ansatz that integrates deep neural networks with tensor-network architectures. In the $\nu$TNS framework, a neural network serves as a disentangler…

Strongly Correlated Electrons · Physics 2026-03-17 Chaohui Fan , Bo Zhan , Yuntian Gu , Tong Liu , Yantao Wu , Mingpu Qin , Dingshun Lv , Tao Xiang