English
Related papers

Related papers: All you need is a good init

200 papers

Residual Network (ResNet) is the state-of-the-art architecture that realizes successful training of really deep neural network. It is also known that good weight initialization of neural network avoids problem of vanishing/exploding…

Machine Learning · Computer Science 2017-10-16 Masato Taki

Training neural networks with first order optimisation methods is at the core of the empirical success of deep learning. The scale of initialisation is a crucial factor, as small initialisations are generally associated to a feature…

Machine Learning · Computer Science 2025-09-16 Etienne Boursier , Nicolas Flammarion

Very deep convolutional neural networks introduced new problems like vanishing gradient and degradation. The recent successful contributions towards solving these problems are Residual and Highway Networks. These networks introduce skip…

Computer Vision and Pattern Recognition · Computer Science 2016-10-06 Anish Shah , Eashan Kadam , Hena Shah , Sameer Shinde , Sandip Shingade

The weight initialization and the activation function of deep neural networks have a crucial impact on the performance of the training procedure. An inappropriate selection can lead to the loss of information of the input during forward…

Machine Learning · Statistics 2018-10-09 Soufiane Hayou , Arnaud Doucet , Judith Rousseau

Deep networks run with low precision operations at inference time offer power and space advantages over high precision alternatives, but need to overcome the challenge of maintaining high accuracy as precision decreases. Here, we present a…

Machine Learning · Computer Science 2020-05-08 Steven K. Esser , Jeffrey L. McKinstry , Deepika Bablani , Rathinakumar Appuswamy , Dharmendra S. Modha

Traditional initialisation methods, e.g. He and Xavier, have been effective in avoiding the problem of vanishing or exploding gradients in neural networks. However, they only use simple pointwise distributions, which model one-dimensional…

Computer Vision and Pattern Recognition · Computer Science 2023-10-26 Christian Harder , Moritz Fuchs , Yuri Tolkach , Anirban Mukhopadhyay

Although weight and activation quantization is an effective approach for Deep Neural Network (DNN) compression and has a lot of potentials to increase inference speed leveraging bit-operations, there is still a noticeable gap in terms of…

Computer Vision and Pattern Recognition · Computer Science 2018-07-27 Dongqing Zhang , Jiaolong Yang , Dongqiangzi Ye , Gang Hua

Existing fine-tuning methods use a single learning rate over all layers. In this paper, first, we discuss that trends of layer-wise weight variations by fine-tuning using a single learning rate do not match the well-known notion that…

Computer Vision and Pattern Recognition · Computer Science 2021-01-05 Youngmin Ro , Jin Young Choi

We present a neural network architecture and training method designed to enable very rapid training and low implementation complexity. Due to its training speed and very few tunable parameters, the method has strong potential for…

Neural and Evolutionary Computing · Computer Science 2015-08-18 Mark D. McDonnell , Tony Vladusich

Convolutional Neural Networks (CNNs) inherently encode strong inductive biases, enabling effective generalization on small-scale datasets. In this paper, we propose integrating this inductive bias into ViTs, not through an architectural…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Jianqiao Zheng , Xueqian Li , Hemanth Saratchandran , Simon Lucey

We investigate hybrid linear-morphological networks. Recent studies highlight the inherent affinity of morphological layers to pruning, but also their difficulty in training. We propose a hybrid network structure, wherein morphological…

Machine Learning · Computer Science 2025-04-15 Konstantinos Fotopoulos , Christos Garoufis , Petros Maragos

We propose a novel method to merge convolutional neural-nets for the inference stage. Given two well-trained networks that may have different architectures that handle different tasks, our method aligns the layers of the original networks…

Computer Vision and Pattern Recognition · Computer Science 2018-05-15 Yi-Min Chou , Yi-Ming Chan , Jia-Hong Lee , Chih-Yi Chiu , Chu-Song Chen

Operating deep neural networks (DNNs) on devices with limited resources requires the reduction of their memory as well as computational footprint. Popular reduction methods are network quantization or pruning, which either reduce the word…

We study in this paper how to initialize the parameters of multinomial logistic regression (a fully connected layer followed with softmax and cross entropy loss), which is widely used in deep neural network (DNN) models for classification…

Computer Vision and Pattern Recognition · Computer Science 2018-09-18 Bowen Cheng , Rong Xiao , Yandong Guo , Yuxiao Hu , Jianfeng Wang , Lei Zhang

Good weight initialization serves as an effective measure to reduce the training cost of a deep neural network (DNN) model. The choice of how to initialize parameters is challenging and may require manual tuning, which can be time-consuming…

Computer Vision and Pattern Recognition · Computer Science 2024-07-17 Yifan Gong , Zheng Zhan , Yanyu Li , Yerlan Idelbayev , Andrey Zharkov , Kfir Aberman , Sergey Tulyakov , Yanzhi Wang , Jian Ren

Normalization techniques have become a basic component in modern convolutional neural networks (ConvNets). In particular, many recent works demonstrate that promoting the orthogonality of the weights helps train deep models and improve…

Computer Vision and Pattern Recognition · Computer Science 2022-01-05 Sheng Liu , Xiao Li , Yuexiang Zhai , Chong You , Zhihui Zhu , Carlos Fernandez-Granda , Qing Qu

Single layer Feedforward Neural Network(FNN) is used many a time as a last layer in models such as seq2seq or could be a simple RNN network. The importance of such layer is to transform the output to our required dimensions. When it comes…

Machine Learning · Computer Science 2018-12-11 Vedanshu , M M Tripathi

It is well known that the initialization of weights in deep neural networks can have a dramatic impact on learning speed. For example, ensuring the mean squared singular value of a network's input-output Jacobian is $O(1)$ is essential for…

Machine Learning · Computer Science 2017-11-15 Jeffrey Pennington , Samuel S. Schoenholz , Surya Ganguli

Recently, a number of iterative learning methods have been introduced to improve generalization. These typically rely on training for longer periods of time in exchange for improved generalization. LLF (later-layer-forgetting) is a…

Recent years have witnessed the great advance of deep learning in a variety of vision tasks. Many state-of-the-art deep neural networks suffer from large size and high complexity, which makes it difficult to deploy in resource-limited…

Computer Vision and Pattern Recognition · Computer Science 2019-05-29 Zhengguang Zhou , Wengang Zhou , Xutao Lv , Xuan Huang , Xiaoyu Wang , Houqiang Li