English
Related papers

Related papers: Implicit Bias of Linear RNNs

200 papers

Learning to remember over long timescales is fundamentally challenging for recurrent neural networks (RNNs). While much prior work has explored why RNNs struggle to learn long timescales and how to mitigate this, we still lack a clear…

Neurons and Cognition · Quantitative Biology 2025-03-25 Blake Bordelon , Jordan Cotler , Cengiz Pehlevan , Jacob A. Zavatone-Veth

The utilization of residual learning has become widespread in deep and scalable neural nets. However, the fundamental principles that contribute to the success of residual learning remain elusive, thus hindering effective training of plain…

Computer Vision and Pattern Recognition · Computer Science 2024-02-14 Tunhou Zhang , Feng Yan , Hai Li , Yiran Chen

Recurrent neural networks have gained widespread use in modeling sequential data. Learning long-term dependencies using these models remains difficult though, due to exploding or vanishing gradients. In this paper, we draw connections…

Machine Learning · Statistics 2019-02-27 Bo Chang , Minmin Chen , Eldad Haber , Ed H. Chi

We introduce a parameter sharing scheme, in which different layers of a convolutional neural network (CNN) are defined by a learned linear combination of parameter tensors from a global bank of templates. Restricting the number of templates…

Machine Learning · Computer Science 2019-03-15 Pedro Savarese , Michael Maire

This work studies approximation based on single-hidden-layer feedforward and recurrent neural networks with randomly generated internal weights. These methods, in which only the last layer of weights and a few hyperparameters are optimized,…

Probability · Mathematics 2021-02-17 Lukas Gonon , Lyudmila Grigoryeva , Juan-Pablo Ortega

Training deep neural networks results in strong learned representations that show good generalization capabilities. In most cases, training involves iterative modification of all weights inside the network via back-propagation. In Extreme…

Machine Learning · Computer Science 2018-02-06 Amir Rosenfeld , John K. Tsotsos

Previous research has shown that fully-connected networks with small initialization and gradient-based training methods exhibit a phenomenon known as condensation during training. This phenomenon refers to the input weights of hidden…

Machine Learning · Computer Science 2023-05-18 Zhangchen Zhou , Hanxu Zhou , Yuqing Li , Zhi-Qin John Xu

Randomized Neural Networks explore the behavior of neural systems where the majority of connections are fixed, either in a stochastic or a deterministic fashion. Typical examples of such systems consist of multi-layered neural network…

Machine Learning · Computer Science 2021-02-03 Claudio Gallicchio , Simone Scardapane

Our understanding of the generalization capabilities of neural networks (NNs) is still incomplete. Prevailing explanations are based on implicit biases of gradient descent (GD) but they cannot account for the capabilities of models from…

Machine Learning · Computer Science 2025-05-01 Damien Teney , Armand Nicolicioiu , Valentin Hartmann , Ehsan Abbasnejad

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

Binary neural networks improve computationally efficiency of deep models with a large margin. However, there is still a performance gap between a successful full-precision training and binary training. We bring some insights about why this…

Machine Learning · Computer Science 2020-04-22 Xinlin Li , Vahid Partovi Nia

Convolutional Neural Networks spread through computer vision like a wildfire, impacting almost all visual tasks imaginable. Despite this, few researchers dare to train their models from scratch. Most work builds on one of a handful of…

Computer Vision and Pattern Recognition · Computer Science 2016-09-26 Philipp Krähenbühl , Carl Doersch , Jeff Donahue , Trevor Darrell

While a diverse collection of continual learning (CL) methods has been proposed to prevent catastrophic forgetting, a thorough investigation of their effectiveness for processing sequential data with recurrent neural networks (RNNs) is…

The brain cortex, which processes visual, auditory and sensory data in the brain, is known to have many recurrent connections within its layers and from higher to lower layers. But, in the case of machine learning with neural networks, it…

Machine Learning · Computer Science 2020-10-22 Sebastian Sanokowski

Recurrent Neural Networks (RNNs) have been proven to be effective in modeling sequential data and they have been applied to boost a variety of tasks such as document classification, speech recognition and machine translation. Most of…

Computation and Language · Computer Science 2018-08-21 Zhiwei Wang , Yao Ma , Dawei Yin , Jiliang Tang

Despite Deep Learning's (DL) empirical success, our theoretical understanding of its efficacy remains limited. One notable paradox is that while conventional wisdom discourages perfect data fitting, deep neural networks are designed to do…

Machine Learning · Computer Science 2024-02-06 Oria Gruber , Haim Avron

We first study the generalization error of models that use a fixed feature representation (frozen intermediate layers) followed by a trainable readout layer. This setting encompasses a range of architectures, from deep random-feature models…

Statistics Theory · Mathematics 2025-11-10 Yessin Moakher , Malik Tiomoko , Cosme Louart , Zhenyu Liao

Recurrent neural networks (RNNs) are known to be difficult to train due to the gradient vanishing and exploding problems and thus difficult to learn long-term patterns and construct deep networks. To address these problems, this paper…

Computer Vision and Pattern Recognition · Computer Science 2020-12-10 Shuai Li , Wanqing Li , Chris Cook , Yanbo Gao

In recent studies, linear recurrent neural networks (LRNNs) have achieved Transformer-level performance in natural language and long-range modeling, while offering rapid parallel training and constant inference cost. With the resurgence of…

Computation and Language · Computer Science 2024-04-10 Ting-Han Fan , Ta-Chung Chi , Alexander I. Rudnicky

Linear Regression and neural networks are widely used to model data. Neural networks distinguish themselves from linear regression with their use of activation functions that enable modeling nonlinear functions. The standard argument for…

Machine Learning · Computer Science 2024-01-02 Anish Lakkapragada