English
Related papers

Related papers: Learning reveals invisible structure in low-rank R…

200 papers

Previous work has shown that DNNs with large depth $L$ and $L_{2}$-regularization are biased towards learning low-dimensional representations of the inputs, which can be interpreted as minimizing a notion of rank $R^{(0)}(f)$ of the learned…

Machine Learning · Computer Science 2024-08-16 Arthur Jacot

We introduce a principled approach for unsupervised structure learning of deep neural networks. We propose a new interpretation for depth and inter-layer connectivity where conditional independencies in the input distribution are encoded…

Machine Learning · Statistics 2018-10-18 Raanan Y. Rohekar , Shami Nisimov , Yaniv Gurwicz , Guy Koren , Gal Novik

Deep neural networks (DNNs) defy the classical bias-variance trade-off: adding parameters to a DNN that interpolates its training data will typically improve its generalization performance. Explaining the mechanism behind this ``benign…

Machine Learning · Statistics 2023-05-02 Diego Doimo , Aldo Glielmo , Sebastian Goldt , Alessandro Laio

Recursive neural networks (RNN) and their recently proposed extension recursive long short term memory networks (RLSTM) are models that compute representations for sentences, by recursively combining word embeddings according to an…

Artificial Intelligence · Computer Science 2016-03-02 Phong Le , Willem Zuidema

Recurrent neural networks have been the dominant models for many speech and language processing tasks. However, we understand little about the behavior and the class of functions recurrent networks can realize. Moreover, the heuristics used…

Computation and Language · Computer Science 2018-11-01 Hao Tang , James Glass

Simple recurrent neural networks (RNNs) and their more advanced cousins LSTMs etc. have been very successful in sequence modeling. Their theoretical understanding, however, is lacking and has not kept pace with the progress for feedforward…

Machine Learning · Computer Science 2021-06-02 Abhishek Panigrahi , Navin Goyal

In a series of recent theoretical works, it was shown that strongly over-parameterized neural networks trained with gradient-based methods could converge exponentially fast to zero training loss, with their parameters hardly varying. In…

Optimization and Control · Mathematics 2020-01-08 Lenaic Chizat , Edouard Oyallon , Francis Bach

Recent experimental studies indicate that synaptic changes induced by neuronal activity are discrete jumps between a small number of stable states. Learning in systems with discrete synapses is known to be a computationally hard problem.…

Neurons and Cognition · Quantitative Biology 2009-11-13 Carlo Baldassi , Alfredo Braunstein , Nicolas Brunel , Riccardo Zecchina

Convolutional neural networks (CNNs) have achieved remarkable performance in various fields, particularly in the domain of computer vision. However, why this architecture works well remains to be a mystery. In this work we move a small step…

Machine Learning · Computer Science 2019-05-27 Bing Yu , Junzhao Zhang , Zhanxing Zhu

Exploiting data invariances is crucial for efficient learning in both artificial and biological neural circuits. Understanding how neural networks can discover appropriate representations capable of harnessing the underlying symmetries of…

Disordered Systems and Neural Networks · Physics 2022-10-17 Alessandro Ingrosso , Sebastian Goldt

The advantage of recurrent neural networks (RNNs) in learning dependencies between time-series data has distinguished RNNs from other deep learning models. Recently, many advances are proposed in this emerging field. However, there is a…

Neural and Evolutionary Computing · Computer Science 2016-02-16 Hojjat Salehinejad

Working memory is a central cognitive ability crucial for intelligent decision-making. Recent experimental and computational work studying working memory has primarily used categorical (i.e., one-hot) inputs, rather than ecologically…

Artificial Intelligence · Computer Science 2024-11-06 Xiaoxuan Lei , Takuya Ito , Pouya Bashivan

Understanding convergent learning -- the degree to which independently trained neural systems -- whether multiple artificial networks or brains and models -- arrive at similar internal representations -- is crucial for both neuroscience and…

Neurons and Cognition · Quantitative Biology 2026-01-26 Chaitanya Kapoor , Sudhanshu Srivastava , Meenakshi Khosla

A robust theoretical framework that can describe and predict the generalization ability of deep neural networks (DNNs) in general circumstances remains elusive. Classical attempts have produced complexity metrics that rely heavily on global…

Machine Learning · Computer Science 2020-01-20 Marelie H. Davel , Marthinus W. Theunissen , Arnold M. Pretorius , Etienne Barnard

Understanding the reasons for the success of deep neural networks trained using stochastic gradient-based methods is a key open problem for the nascent theory of deep learning. The types of data where these networks are most successful,…

Machine Learning · Statistics 2020-12-04 Sebastian Goldt , Marc Mézard , Florent Krzakala , Lenka Zdeborová

Integrating task-relevant information into neural representations is a fundamental ability of both biological and artificial intelligence systems. Recent theories have categorized learning into two regimes: the rich regime, where neural…

Machine Learning · Computer Science 2025-07-14 Chi-Ning Chou , Hang Le , Yichen Wang , SueYeon Chung

Recurrent neural networks (RNNs) are widely used throughout neuroscience as models of local neural activity. Many properties of single RNNs are well characterized theoretically, but experimental neuroscience has moved in the direction of…

Machine Learning · Computer Science 2023-01-31 Leo Kozachkov , Michaela Ennis , Jean-Jacques Slotine

Advancements in artificial intelligence call for a deeper understanding of the fundamental mechanisms underlying deep learning. In this work, we propose a theoretical framework to analyze learning dynamics through the lens of dynamical…

Machine Learning · Computer Science 2025-10-13 Yuchen Lin , Yong Zhang , Sihan Feng , Hong Zhao

Recurrent neural networks (RNNs) are machine learning models widely used for learning temporal relationships. Current state-of-the-art RNNs use integrating or spiking neurons -- two classes of computing units whose outputs depend directly…

Neural and Evolutionary Computing · Computer Science 2025-06-10 Peter DelMastro , Arjun Karuvally , Hananel Hazan , Hava Siegelmann , Edward Rietman

Much of the recent research on solving iterative inference problems focuses on moving away from hand-chosen inference algorithms and towards learned inference. In the latter, the inference process is unrolled in time and interpreted as a…

Neural and Evolutionary Computing · Computer Science 2017-06-14 Patrick Putzky , Max Welling