English
Related papers

Related papers: Exploring Neural Network Landscapes: Star-Shaped a…

200 papers

Deep learning has received considerable empirical successes in recent years. However, while many ad hoc tricks have been discovered by practitioners, until recently, there has been a lack of theoretical understanding for tricks invented in…

Machine Learning · Computer Science 2020-12-29 Cong Fang , Hanze Dong , Tong Zhang

We show how a Hopfield network with modifiable recurrent connections undergoing slow Hebbian learning can extract the underlying geometry of an input space. First, we use a slow/fast analysis to derive an averaged system whose dynamics…

Neurons and Cognition · Quantitative Biology 2011-02-02 Mathieu N. Galtier , Olivier D. Faugeras , Paul C. Bressloff

A main puzzle of deep networks revolves around the absence of overfitting despite large overparametrization and despite the large capacity demonstrated by zero training error on randomly labeled data. In this note, we show that the dynamics…

State-space models (SSMs) have become a cornerstone for unraveling brain dynamics, revealing how latent neural states evolve over time and give rise to observed signals. By combining the flexibility of deep learning with the principled…

Machine Learning · Computer Science 2026-02-03 Tingting Dan , Jiaqi Ding , Guorong Wu

Studies of the dynamics of nonlinear recurrent neural networks often assume independent and identically distributed couplings, but large-scale connectomics data indicate that biological neural circuits exhibit markedly different…

Neurons and Cognition · Quantitative Biology 2025-10-28 David G. Clark , Owen Marschall , Alexander van Meegen , Ashok Litwin-Kumar

The topological structure of complex networks has fascinated researchers for several decades, resulting in the discovery of many universal properties and reoccurring characteristics of different kinds of networks. However, much less is…

Social and Information Networks · Computer Science 2017-06-28 Yvonne Anne Pignolet , Matthieu Roy , Stefan Schmid , Gilles Tredan

The topological structure of complex networks has fascinated researchers for several decades, resulting in the discovery of many universal properties and reoccurring characteristics of different kinds of networks. However, much less is…

Social and Information Networks · Computer Science 2017-03-02 Yvonne Anne Pignolet , Matthieu Roy , Stefan Schmid , Gilles Tredan

We analyze recurrent neural networks with diagonal hidden-to-hidden weight matrices, trained with gradient descent in the supervised learning setting, and prove that gradient descent can achieve optimality \emph{without} massive…

Machine Learning · Computer Science 2024-10-11 Semih Cayci , Atilla Eryilmaz

Cosmic connectivity and multiplicity, i.e. the number of filaments globally or locally connected to a given cluster is a natural probe of the growth of structure and in particular of the nature of dark energy. It is also a critical…

Cosmology and Nongalactic Astrophysics · Physics 2018-10-22 Sandrine Codis , Dmitri Pogosyan , Christophe Pichon

We provide the first global optimization landscape analysis of $Neural\;Collapse$ -- an intriguing empirical phenomenon that arises in the last-layer classifiers and features of neural networks during the terminal phase of training. As…

Machine Learning · Computer Science 2021-05-07 Zhihui Zhu , Tianyu Ding , Jinxin Zhou , Xiao Li , Chong You , Jeremias Sulam , Qing Qu

We consider a one-dimensional network in which the nodes at Euclidean distance $l$ can have long range connections with a probabilty $P(l) \sim l^{-\delta}$ in addition to nearest neighbour connections. This system has been shown to exhibit…

Statistical Mechanics · Physics 2009-11-07 Parongama Sen , Kinjal Banerjee , Turbasu Biswas

We propose a novel way of reducing the number of parameters in the storage-hungry fully connected layers of a neural network by using pre-defined sparsity, where the majority of connections are absent prior to starting training. Our results…

Machine Learning · Computer Science 2019-04-29 Sourya Dey , Kuan-Wen Huang , Peter A. Beerel , Keith M. Chugg

Randomly connected neural networks have long served as a theoretical tool for studying collective dynamics in neural populations, yet quantitative comparisons to experiments remain limited. Recent technological advances have made it…

Neurons and Cognition · Quantitative Biology 2026-05-27 Zehui Zhao , Michael J Pasek , Ilya M Nemenman

A major issue in biology is the understanding of the interactions between proteins. These interactions can be described by a network, where the proteins are modeled by nodes and the interactions by edges. The origin of these protein…

Biological Physics · Physics 2011-08-01 Christian M. Schneider , Lucilla de Arcangelis , Hans J. Herrmann

We prove that finding all globally optimal two-layer ReLU neural networks can be performed by solving a convex optimization program with cone constraints. Our analysis is novel, characterizes all optimal solutions, and does not leverage…

Machine Learning · Computer Science 2022-03-15 Yifei Wang , Jonathan Lacotte , Mert Pilanci

Deep neural networks are workhorse models in machine learning with multiple layers of non-linear functions composed in series. Their loss function is highly non-convex, yet empirically even gradient descent minimisation is sufficient to…

Disordered Systems and Neural Networks · Physics 2020-03-18 Simon Becker , Yao Zhang , Alpha A. Lee

Random network models play a prominent role in modeling, analyzing and understanding complex phenomena on real-life networks. However, a key property of networks is often neglected: many real-world networks exhibit spatial structure, the…

Quantitative Methods · Quantitative Biology 2017-02-07 John Lang , Hans De Sterck , Jamieson L. Kaiser , Joel C. Miller

Modern data analysis pipelines are becoming increasingly complex due to the presence of multi-view information sources. While graphs are effective in modeling complex relationships, in many scenarios a single graph is rarely sufficient to…

Machine Learning · Statistics 2019-04-02 Uday Shankar Shanthamallu , Jayaraman J. Thiagarajan , Huan Song , Andreas Spanias

Geometric deep learning has gained much attention in recent years due to more available data acquired from non-Euclidean domains. Some examples include point clouds for 3D models and wireless sensor networks in communications. Graphs are…

Signal Processing · Electrical Eng. & Systems 2022-10-04 Zhiyang Wang , Luana Ruiz , Alejandro Ribeiro

Elements of networks interact in many ways, so modeling them with graphs requires multiple types of edges (or network layers). Here we show that such multiplex networks are generically more vulnerable to global cascades than simplex…

Physics and Society · Physics 2012-05-01 Charles D. Brummitt , Kyu-Min Lee , K. -I. Goh
‹ Prev 1 8 9 10 Next ›