English
Related papers

Related papers: Implicit Bias of Linear RNNs

200 papers

Diagonal linear networks are neural networks with linear activation and diagonal weight matrices. Their theoretical interest is that their implicit regularization can be rigorously analyzed: from a small initialization, the training of…

Machine Learning · Computer Science 2026-03-19 Raphaël Berthier

In recent years significant progress has been made in successfully training recurrent neural networks (RNNs) on sequence learning problems involving long range temporal dependencies. The progress has been made on three fronts: (a)…

Neural and Evolutionary Computing · Computer Science 2016-06-24 Sachin S. Talathi , Aniket Vartak

Representation learning, i.e. the generation of representations useful for downstream applications, is a task of fundamental importance that underlies much of the success of deep neural networks (DNNs). Recently, robustness to adversarial…

Machine Learning · Computer Science 2022-09-16 Christian Cianfarani , Arjun Nitin Bhagoji , Vikash Sehwag , Ben Y. Zhao , Prateek Mittal , Haitao Zheng

Even though dense networks have lost importance today, they are still used as final logic elements. It could be shown that these dense networks can be simplified by the sparse graph interpretation. This in turn shows that the information…

Neural and Evolutionary Computing · Computer Science 2018-09-25 Thomas Pircher , Dominik Haspel , Eberhard Schlücker

Recurrent Neural Network (RNN) and its variations such as Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU), have become standard building blocks for learning online data of sequential nature in many research areas, including…

Computation and Language · Computer Science 2020-05-12 Enmao Diao , Jie Ding , Vahid Tarokh

Implicit Neural Representations (INRs) are powerful to parameterize continuous signals in computer vision. However, almost all INRs methods are limited to low-level tasks, e.g., image/video compression, super-resolution, and image…

Computer Vision and Pattern Recognition · Computer Science 2023-12-04 Yiran Song , Qianyu Zhou , Lizhuang Ma

Recurrent neural networks are extremely powerful yet hard to train. One of their issues is the vanishing gradient problem, whereby propagation of training signals may be exponentially attenuated, freezing training. Use of orthogonal or…

Machine Learning · Computer Science 2023-02-16 Marcelo O. Magnasco

We investigate the computational complexity of various problems for simple recurrent neural networks (RNNs) as formal models for recognizing weighted languages. We focus on the single-layer, ReLU-activation, rational-weight RNNs with…

Formal Languages and Automata Theory · Computer Science 2018-03-06 Yining Chen , Sorcha Gilroy , Andreas Maletti , Jonathan May , Kevin Knight

Training recurrent neural networks (RNNs) is a high-dimensional process that requires updating numerous parameters. Therefore, it is often difficult to pinpoint the underlying learning mechanisms. To address this challenge, we propose to…

Neurons and Cognition · Quantitative Biology 2025-02-12 Udith Haputhanthri , Liam Storan , Yiqi Jiang , Tarun Raheja , Adam Shai , Orhun Akengin , Nina Miolane , Mark J. Schnitzer , Fatih Dinc , Hidenori Tanaka

We present an architecture of a recurrent neural network (RNN) with a fully-connected deep neural network (DNN) as its feature extractor. The RNN is equipped with both causal temporal prediction and non-causal look-ahead, via…

Machine Learning · Computer Science 2014-03-07 Jianshu Chen , Li Deng

Modern deep learning models generalize remarkably well in-distribution, despite being overparametrized and trained with little to no explicit regularization. Instead, current theory credits implicit regularization imposed by the choice of…

Machine Learning · Computer Science 2026-03-17 Jonathan Wenger , Beau Coker , Juraj Marusic , John P. Cunningham

Recurrent Neural Networks (RNNs) with Long Short-Term Memory units (LSTM) are widely used because they are expressive and are easy to train. Our interest lies in empirically evaluating the expressiveness and the learnability of LSTMs in the…

Neural and Evolutionary Computing · Computer Science 2015-11-24 Wojciech Zaremba , Ilya Sutskever

Recurrent networks of spiking neurons (RSNNs) underlie the astounding computing and learning capabilities of the brain. But computing and learning capabilities of RSNN models have remained poor, at least in comparison with artificial neural…

Neural and Evolutionary Computing · Computer Science 2018-12-27 Guillaume Bellec , Darjan Salaj , Anand Subramoney , Robert Legenstein , Wolfgang Maass

Time series prediction is essential for human activities in diverse areas. A common approach to this task is to harness Recurrent Neural Networks (RNNs). However, while their predictions are quite accurate, their learning process is complex…

Quantum Physics · Physics 2025-05-30 Michał Siemaszko , Adam Buraczewski , Bertrand Le Saux , Magdalena Stobińska

The Recurrent Neural Networks and their variants have shown promising performances in sequence modeling tasks such as Natural Language Processing. These models, however, turn out to be impractical and difficult to train when exposed to very…

Computer Vision and Pattern Recognition · Computer Science 2017-07-07 Yinchong Yang , Denis Krompass , Volker Tresp

Neural networks trained on standard image classification data sets are shown to be less resistant to data set bias. It is necessary to comprehend the behavior objective function that might correspond to superior performance for data with…

Machine Learning · Computer Science 2022-11-16 Gnyanesh Bangaru , Lalith Bharadwaj Baru , Kiran Chakravarthula

We study the approximation properties and optimization dynamics of recurrent neural networks (RNNs) when applied to learn input-output relationships in temporal data. We consider the simple but representative setting of using…

Machine Learning · Computer Science 2024-09-02 Zhong Li , Jiequn Han , Weinan E , Qianxiao Li

The study of deep neural networks (DNNs) in the infinite-width limit, via the so-called neural tangent kernel (NTK) approach, has provided new insights into the dynamics of learning, generalization, and the impact of initialization. One key…

Machine Learning · Computer Science 2021-06-16 Sina Alemohammad , Zichao Wang , Randall Balestriero , Richard Baraniuk

Bidirectional recurrent neural networks (RNN) are trained to predict both in the positive and negative time directions simultaneously. They have not been used commonly in unsupervised tasks, because a probabilistic interpretation of the…

Machine Learning · Computer Science 2015-11-03 Mathias Berglund , Tapani Raiko , Mikko Honkala , Leo Kärkkäinen , Akos Vetek , Juha Karhunen

We introduce WARP (Weight-space Adaptive Recurrent Prediction), a simple yet powerful model that unifies weight-space learning with linear recurrence to redefine sequence modeling. Unlike conventional recurrent neural networks (RNNs) which…