English
Related papers

Related papers: Structured First-Layer Initialization Pre-Training…

200 papers

Shallow supervised 1-hidden layer neural networks have a number of favorable properties that make them easier to interpret, analyze, and optimize than their deep counterparts, but lack their representational power. Here we use 1-hidden…

Machine Learning · Computer Science 2019-04-24 Eugene Belilovsky , Michael Eickenberg , Edouard Oyallon

Weight initialization is important for faster convergence and stability of deep neural networks training. In this paper, a robust initialization method is developed to address the training instability in long short-term memory (LSTM)…

Spiking Neural Networks (SNNs) are brain-inspired, event-driven machine learning algorithms that have been widely recognized in producing ultra-high-energy-efficient hardware. Among existing SNNs, unsupervised SNNs based on synaptic…

Neural and Evolutionary Computing · Computer Science 2022-09-20 Mingyuan Meng , Xingyu Yang , Lei Bi , Jinman Kim , Shanlin Xiao , Zhiyi Yu

A common challenge in regression is that for many problems, the degrees of freedom required for a high-quality solution also allows for overfitting. Regularization is a class of strategies that seek to restrict the range of possible…

Machine Learning · Computer Science 2022-11-15 Colin Ponce , Ruipeng Li , Christina Mao , Panayot Vassilevski

Federated Learning (FL) is an emerging paradigm that allows a model to be trained across a number of participants without sharing data. Recent works have begun to consider the effects of using pre-trained models as an initialization point…

Machine Learning · Computer Science 2023-11-07 Gwen Legate , Nicolas Bernier , Lucas Caccia , Edouard Oyallon , Eugene Belilovsky

We propose an incremental training method that partitions the original network into sub-networks, which are then gradually incorporated in the running network during the training process. To allow for a smooth dynamic growth of the network,…

Machine Learning · Computer Science 2018-03-29 Roxana Istrate , Adelmo Cristiano Innocenza Malossi , Costas Bekas , Dimitrios Nikolopoulos

Deep reinforcement learning (RL) is increasingly deployed in resource-constrained environments, yet the go-to function approximators - multilayer perceptrons (MLPs) - are often parameter-inefficient due to an imperfect inductive bias for…

Machine Learning · Computer Science 2026-02-02 Rajib Mostakim , Reza T. Batley , Sourav Saha

Spiking Neural Networks (SNNs) have been attached great importance due to the distinctive properties of low power consumption, biological plausibility, and adversarial robustness. The most effective way to train deep SNNs is through…

Neural and Evolutionary Computing · Computer Science 2022-02-04 Tong Bu , Jianhao Ding , Zhaofei Yu , Tiejun Huang

We propose a simple architecture for deep reinforcement learning by embedding inputs into a learned Fourier basis and show that it improves the sample efficiency of both state-based and image-based RL. We perform infinite-width analysis of…

Machine Learning · Computer Science 2021-12-07 Alexander C. Li , Deepak Pathak

Batch normalization (BN) has become a critical component across diverse deep neural networks. The network with BN is invariant to positively linear re-scale transformation, which makes there exist infinite functionally equivalent networks…

Machine Learning · Computer Science 2022-06-07 Mingyang Yi

This paper proposes an unsupervised learning-based precoding framework that trains deep neural networks (DNNs) with no target labels by unfolding an interior point method (IPM) proximal `log' barrier function. The proximal `log' barrier…

Signal Processing · Electrical Eng. & Systems 2021-10-20 Abdullahi Mohammad , Christos Masouros , Yiannis Andreopoulos

In this work, we propose a data-driven scheme to initialize the parameters of a deep neural network. This is in contrast to traditional approaches which randomly initialize parameters by sampling from transformed standard distributions.…

Neural and Evolutionary Computing · Computer Science 2021-05-24 Debasmit Das , Yash Bhalgat , Fatih Porikli

In this work, we propose a multi-stage training strategy for the development of deep learning algorithms applied to problems with multiscale features. Each stage of the pro-posed strategy shares an (almost) identical network structure and…

Numerical Analysis · Mathematics 2020-09-25 Eric Chung , Wing Tat Leung , Sai-Mang Pun , Zecheng Zhang

Gradient-based optimization has been a cornerstone of machine learning that enabled the vast advances of Artificial Intelligence (AI) development over the past decades. However, this type of optimization requires differentiation, and with…

Spiking neural networks (SNNs) have closer dynamics to the brain than current deep neural networks. Their low power consumption and sample efficiency make these networks interesting. Recently, several deep convolutional spiking neural…

Computer Vision and Pattern Recognition · Computer Science 2022-11-01 Shahriar Rezghi Shirsavar , Mohammad-Reza A. Dehaqani

Spiking Neural Networks (SNNs), with their event-driven and biologically inspired operation, are well-suited for energy-efficient neuromorphic hardware. Neural coding, critical to SNNs, determines how information is represented via spikes.…

Neural and Evolutionary Computing · Computer Science 2025-03-11 Kaiwei Che , Wei Fang , Zhengyu Ma , Yifan Huang , Peng Xue , Li Yuan , Timothée Masquelier , Yonghong Tian

Symbol Level Precoding (SLP) has attracted significant research interest due to its ability to exploit interference for energy-efficient transmission. This paper proposes an unsupervised deep-neural network (DNN) based SLP framework.…

Signal Processing · Electrical Eng. & Systems 2021-11-17 Abdullahi Mohammad , Christos Masouros , Yiannis Andreopoulos

Proper initialisation strategy is of primary importance to mitigate gradient explosion or vanishing when training neural networks. Yet, the impact of initialisation parameters still lacks a precise theoretical understanding for several…

Machine Learning · Computer Science 2026-05-12 Andrea Combette , Antoine Venaille , Nelly Pustelnik

We propose a novel learning method for multilayered neural networks which uses feedforward supervisory signal and associates classification of a new input with that of pre-trained input. The proposed method effectively uses rich input…

Neural and Evolutionary Computing · Computer Science 2015-02-17 Takashi Shinozaki , Yasushi Naruse

Despite the recent success of stochastic gradient descent in deep learning, it is often difficult to train a deep neural network with an inappropriate choice of its initial parameters. Even if training is successful, it has been known that…

Machine Learning · Computer Science 2023-02-10 Cheolhyoung Lee , Kyunghyun Cho
‹ Prev 1 4 5 6 7 8 10 Next ›