English
Related papers

Related papers: Jamming in multilayer supervised learning models

200 papers

We construct and analyze a family of $M$-component vectorial spin systems which exhibit glass transitions and jamming within supercooled paramagnetic states without quenched disorder. Our system is defined on lattices with connectivity…

Statistical Mechanics · Physics 2018-06-27 Hajime Yoshino

We present Multi-Scale Label Dependence Relation Networks (MSDN), a novel approach to multi-label classification (MLC) using 1-dimensional convolution kernels to learn label dependencies at multi-scale. Modern multi-label classifiers have…

Machine Learning · Computer Science 2021-07-14 Junhyung Kim , Byungyoon Park , Charmgil Hong

Understanding how biological constraints shape neural computation is a central goal of computational neuroscience. Spatially embedded recurrent neural networks provide a promising avenue to study how modelled constraints shape the combined…

Neural and Evolutionary Computing · Computer Science 2024-09-27 Cornelia Sheeran , Andrew S. Ham , Duncan E. Astle , Jascha Achterberg , Danyal Akarca

State-of-the-art 2D image compression schemes rely on the power of convolutional neural networks (CNNs). Although CNNs offer promising perspectives for 2D image compression, extending such models to omnidirectional images is not…

Image and Video Processing · Electrical Eng. & Systems 2022-09-21 Navid Mahmoudian Bidgoli , Roberto G. de A. Azevedo , Thomas Maugey , Aline Roumy , Pascal Frossard

Recurrent neural networks (RNNs) are powerful architectures to model sequential data, due to their capability to learn short and long-term dependencies between the basic elements of a sequence. Nonetheless, popular tasks such as speech or…

The design of recurrent neural networks (RNNs) to accurately process sequential inputs with long-time dependencies is very challenging on account of the exploding and vanishing gradient problem. To overcome this, we propose a novel RNN…

Machine Learning · Computer Science 2021-08-19 T. Konstantin Rusch , Siddhartha Mishra

A class of shape-invariant bound-state problems which represent transitions in a two-level system introduced earlier are generalized to include arbitrary energy splittings between the two levels. We show that the coupled-channel…

Quantum Physics · Physics 2007-05-23 A. N. F. Aleixo , A. B. Balantekin , M. A. Candido Ribeiro

To understand the training dynamics of neural networks (NNs), prior studies have considered the infinite-width mean-field (MF) limit of two-layer NN, establishing theoretical guarantees of its convergence under gradient flow training as…

Machine Learning · Computer Science 2022-10-31 Zhengdao Chen , Eric Vanden-Eijnden , Joan Bruna

Deep neural networks are widely used prediction algorithms whose performance often improves as the number of weights increases, leading to over-parametrization. We consider a two-layered neural network whose first layer is frozen while the…

Machine Learning · Computer Science 2023-04-10 Roman Worschech , Bernd Rosenow

We introduce a learning-based algorithm to obtain a measurement matrix for compressive sensing related recovery problems. The focus lies on matrices with a constant modulus constraint which typically represent a network of analog phase…

Signal Processing · Electrical Eng. & Systems 2021-10-15 Michael Koller , Wolfgang Utschick

Based on deep neural networks (DNNs), deep learning has been successfully applied to many problems, but its mechanism is still not well understood -- especially the reason why over-parametrized DNNs can generalize. A recent statistical…

Disordered Systems and Neural Networks · Physics 2025-06-10 Gang Huang , Lai Shun Chan , Hajime Yoshino , Ge Zhang , Yuliang Jin

Jamming and percolation transitions in the standard random sequential adsorption of particles on regular lattices are characterized by a universal set of critical exponents. The universality class is preserved even in the presence of…

Statistical Mechanics · Physics 2021-04-28 Sumanta Kundu , Dipanjan Mandal

This work suggests using sampling theory to analyze the function space represented by neural networks. First, it shows, under the assumption of a finite input domain, which is the common case in training neural networks, that the function…

Machine Learning · Computer Science 2022-02-28 Raja Giryes

We present a classical kinetically constrained model of interacting particles on a triangular ladder, which displays diffusion and jamming and can be treated by means of a classical-quantum mapping. Interpreted as a theory of interacting…

Statistical Mechanics · Physics 2025-05-16 Abhishek Raj , Vadim Oganesyan , Antonello Scardicchio

As a function of packing fraction at zero temperature and applied stress, an amorphous packing of spheres exhibits a jamming transition where the system is sensitive to boundary conditions even in the thermodynamic limit. Upon further…

Soft Condensed Matter · Physics 2013-11-25 Samuel S. Schoenholz , Carl P. Goodrich , Oleg Kogan , Andrea J. Liu , Sidney R. Nagel

A fundamental property of deep learning normalization techniques, such as batch normalization, is making the pre-normalization parameters scale invariant. The intrinsic domain of such parameters is the unit sphere, and therefore their…

Machine Learning · Computer Science 2023-01-18 Maxim Kodryan , Ekaterina Lobacheva , Maksim Nakhodnov , Dmitry Vetrov

Distributions of data or sensory stimuli often enjoy underlying invariances. How and to what extent those symmetries are captured by unsupervised learning methods is a relevant question in machine learning and in computational neuroscience.…

Disordered Systems and Neural Networks · Physics 2020-06-24 Moshir Harsh , Jérôme Tubiana , Simona Cocco , Remi Monasson

Countless learning tasks require dealing with sequential data. Image captioning, speech synthesis, and music generation all require that a model produce outputs that are sequences. In other domains, such as time series prediction, video…

Machine Learning · Computer Science 2015-10-20 Zachary C. Lipton , John Berkowitz , Charles Elkan

Speech discrete representation has proven effective in various downstream applications due to its superior compression rate of the waveform, fast convergence during training, and compatibility with other modalities. Discrete units extracted…

Sound · Computer Science 2024-06-17 Jiatong Shi , Xutai Ma , Hirofumi Inaguma , Anna Sun , Shinji Watanabe

Machine learning (ML) models have achieved strikingly high accuracies in spectroscopic classification tasks, often without a clear proof that those models used chemically meaningful features. Existing studies have linked these results to…

Machine Learning · Computer Science 2026-04-07 Umberto Michelucci , Francesca Venturini