English
Related papers

Related papers: ReZero is All You Need: Fast Convergence at Large …

200 papers

Densely Connected Convolutional Networks (DenseNets) have been shown to achieve state-of-the-art results on image classification tasks while using fewer parameters and computation than competing methods. Since each layer in this…

Computer Vision and Pattern Recognition · Computer Science 2018-06-07 Andy Hess

PCANet and its variants provided good accuracy results for classification tasks. However, despite the importance of network depth in achieving good classification accuracy, these networks were trained with a maximum of nine layers. In this…

Computer Vision and Pattern Recognition · Computer Science 2023-01-30 Mubarakah Alotaibi , Richard Wilson

Artificial neural networks are most commonly trained with the back-propagation algorithm, where the gradient for learning is provided by back-propagating the error, layer by layer, from the output layer to the hidden layers. A recently…

Machine Learning · Statistics 2016-12-22 Arild Nøkland

Deep learning models offer superior performance compared to other machine learning techniques for a variety of tasks and domains, but pose their own challenges. In particular, deep learning models require larger training times as the depth…

Machine Learning · Computer Science 2023-05-31 Sunitha Basodi , Krishna Pusuluri , Xueli Xiao , Yi Pan

This paper introduces a new architectural framework, known as input fast-forwarding, that can enhance the performance of deep networks. The main idea is to incorporate a parallel path that sends representations of input values forward to…

Computer Vision and Pattern Recognition · Computer Science 2017-05-25 Ahmed Ibrahim , A. Lynn Abbott , Mohamed E. Hussein

The increasing complexity of deep learning architectures is resulting in training time requiring weeks or even months. This slow training is due in part to vanishing gradients, in which the gradients used by back-propagation are extremely…

Computer Vision and Pattern Recognition · Computer Science 2015-10-16 Bharat Singh , Soham De , Yangmuzi Zhang , Thomas Goldstein , Gavin Taylor

Traditional physics-based approaches to infer sub-surface properties such as full-waveform inversion or reflectivity inversion are time-consuming and computationally expensive. We present a deep-learning technique that eliminates the need…

Very deep convolutional neural networks (CNNs) yield state of the art results on a wide variety of visual recognition problems. A number of state of the the art methods for image recognition are based on networks with well over 100 layers…

Computer Vision and Pattern Recognition · Computer Science 2016-07-15 Joel Moniz , Christopher Pal

Very deep convolutional neural networks offer excellent recognition results, yet their computational expense limits their impact for many real-world applications. We introduce BlockDrop, an approach that learns to dynamically choose which…

Computer Vision and Pattern Recognition · Computer Science 2019-01-29 Zuxuan Wu , Tushar Nagarajan , Abhishek Kumar , Steven Rennie , Larry S. Davis , Kristen Grauman , Rogerio Feris

In the pursuit of reducing the number of trainable parameters in deep transformer networks, we employ Reinforcement Learning to dynamically select layers during training and tie them together. Every few iterations, the RL agent is asked…

Machine Learning · Computer Science 2024-01-24 Tamir David Hay , Lior Wolf

Recurrent neural network architectures can have useful computational properties, with complex temporal dynamics and input-sensitive attractor states. However, evaluation of recurrent dynamic architectures requires solution of systems of…

Neural and Evolutionary Computing · Computer Science 2019-11-18 Dylan Richard Muir

Residual networks (ResNet) and weight normalization play an important role in various deep learning applications. However, parameter initialization strategies have not been studied previously for weight normalized networks and, in practice,…

Machine Learning · Statistics 2019-10-31 Devansh Arpit , Victor Campos , Yoshua Bengio

Large language models (LLMs) often struggle with strict memory, latency, and power demands. To meet these demands, various forms of dynamic sparsity have been proposed that reduce compute on an input-by-input basis. These methods improve…

Computation and Language · Computer Science 2024-04-09 Jordan Dotzel , Yash Akhauri , Ahmed S. AbouElhamayed , Carly Jiang , Mohamed Abdelfattah , Zhiru Zhang

In recent years, there has been a surge in applying deep learning to various challenging design problems in communication networks. The early attempts adopt neural architectures inherited from applications such as computer vision, which…

Information Theory · Computer Science 2022-03-22 Yifei Shen , Jun Zhang , Khaled B. Letaief

Scaling network depth has been a central driver behind the success of modern foundation models, yet recent investigations suggest that deep layers are often underutilized. This paper revisits the default mechanism for deepening neural…

Machine Learning · Computer Science 2026-02-10 Yilang Zhang , Bingcong Li , Niao He , Georgios B. Giannakis

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

Training very deep convolutional networks is challenging, requiring significant computational resources and time. Existing acceleration methods often depend on specific architectures or require network modifications. We introduce…

Computer Vision and Pattern Recognition · Computer Science 2024-12-25 Evgeny Hershkovitch Neiterman , Gil Ben-Artzi

In comparison to classical shallow representation learning techniques, deep neural networks have achieved superior performance in nearly every application benchmark. But despite their clear empirical advantages, it is still not well…

Machine Learning · Computer Science 2022-01-11 Calvin Murdock , George Cazenavette , Simon Lucey

This paper addresses the understanding and characterization of residual networks (ResNet), which are among the state-of-the-art deep learning architectures for a variety of supervised learning problems. We focus on the mapping component of…

Computer Vision and Pattern Recognition · Computer Science 2018-06-25 Francois Rousseau , Ronan Fablet

Despite being the cornerstone of deep learning, backpropagation is criticized for its inherent sequentiality, which can limit the scalability of very deep models. Such models faced convergence issues due to vanishing gradient, later…

Machine Learning · Computer Science 2025-04-01 Erwan Fagnou , Paul Caillon , Blaise Delattre , Alexandre Allauzen