English
Related papers

Related papers: ZNorm: Z-Score Gradient Normalization Accelerating…

200 papers

Deep learning networks are typically trained by Stochastic Gradient Descent (SGD) methods that iteratively improve the model parameters by estimating a gradient on a very small fraction of the training data. A major roadblock faced when…

Machine Learning · Computer Science 2020-06-11 Tao Lin , Lingjing Kong , Sebastian U. Stich , Martin Jaggi

In standard neural network training, the gradients in the backward pass are determined by the forward pass. As a result, the two stages are coupled. This is how most neural networks are trained currently. However, gradient modification in…

Machine Learning · Computer Science 2022-09-21 Bishshoy Das , Milton Mondal , Brejesh Lall , Shiv Dutt Joshi , Sumantra Dutta Roy

This paper presents a novel technique based on gradient boosting to train the final layers of a neural network (NN). Gradient boosting is an additive expansion algorithm in which a series of models are trained sequentially to approximate a…

Machine Learning · Computer Science 2023-05-05 Seyedsaman Emami , Gonzalo Martínez-Muñoz

In this paper, we present GradPIM, a processing-in-memory architecture which accelerates parameter updates of deep neural networks training. As one of processing-in-memory techniques that could be realized in the near future, we propose an…

Machine Learning · Computer Science 2021-02-16 Heesu Kim , Hanmin Park , Taehyun Kim , Kwanheum Cho , Eojin Lee , Soojung Ryu , Hyuk-Jae Lee , Kiyoung Choi , Jinho Lee

Spiking Neural Networks (SNNs) as Machine Learning (ML) models have recently received a lot of attention as a potentially more energy-efficient alternative to conventional Artificial Neural Networks. The non-differentiability and sparsity…

Machine Learning · Computer Science 2025-12-05 Maximilian Gollwitzer , Felix Dietrich

Deep Neural Networks (DNNs) training can be difficult due to vanishing and exploding gradients during weight optimization through backpropagation. To address this problem, we propose a general class of Hamiltonian DNNs (H-DNNs) that stem…

Machine Learning · Computer Science 2023-01-02 Clara Lucía Galimberti , Luca Furieri , Liang Xu , Giancarlo Ferrari-Trecate

Denoising generative models deliver high-fidelity generation but remain bottlenecked by inference latency due to the many iterative denoiser calls required during sampling. Training-free acceleration methods reduce latency by either…

Machine Learning · Computer Science 2026-04-03 Yixiao Wang , Ting Jiang , Zishan Shao , Hancheng Ye , Jingwei Sun , Mingyuan Ma , Jianyi Zhang , Yiran Chen , Hai Li

Deep Neural Networks (DNNs) provide state-of-the-art solutions in several difficult machine perceptual tasks. However, their performance relies on the availability of a large set of labeled training data, which limits the breadth of their…

Machine Learning · Computer Science 2018-03-01 Randall Balestriero , Herve Glotin , Richard Baraniuk

Despite the rapid progress of neuromorphic computing, the inadequate depth and the resulting insufficient representation power of spiking neural networks (SNNs) severely restrict their application scope in practice. Residual learning and…

Neural and Evolutionary Computing · Computer Science 2022-02-18 Yifan Hu , Yujie Wu , Lei Deng , Guoqi Li

Graph neural networks (GNNs) have been demonstrated to achieve state-of-the-art for a number of graph-based learning tasks, which leads to a rise in their employment in various domains. However, it has been shown that GNNs may inherit and…

Machine Learning · Computer Science 2022-05-23 O. Deniz Kose , Yanning Shen

Adaptive "life-long" learning at the edge and during online task performance is an aspirational goal of AI research. Neuromorphic hardware implementing Spiking Neural Networks (SNNs) are particularly attractive in this regard, as their…

Neural and Evolutionary Computing · Computer Science 2022-01-27 Kenneth Stewart , Emre Neftci

Depthwise separable convolution has shown great efficiency in network design, but requires time-consuming training procedure with full training-set available. This paper first analyzes the mathematical relationship between regular…

Computer Vision and Pattern Recognition · Computer Science 2018-08-17 Jianbo Guo , Yuxi Li , Weiyao Lin , Yurong Chen , Jianguo Li

Dynamic DNN optimization techniques such as layer-skipping offer increased adaptability and efficiency gains but can lead to i) a larger memory footprint as in decision gates, ii) increased training complexity (e.g., with non-differentiable…

Machine Learning · Computer Science 2025-05-26 Guilherme Korol , Antonio Carlos Schneider Beck , Jeronimo Castrillon

The simplicity of gradient descent (GD) made it the default method for training ever-deeper and complex neural networks. Both loss functions and architectures are often explicitly tuned to be amenable to this basic local optimization. In…

Machine Learning · Computer Science 2019-04-30 Dmitrii Marin , Meng Tang , Ismail Ben Ayed , Yuri Boykov

In this paper, we propose a novel optimization algorithm for training machine learning models called Input Normalized Stochastic Gradient Descent (INSGD), inspired by the Normalized Least Mean Squares (NLMS) algorithm used in adaptive…

Machine Learning · Computer Science 2023-06-28 Salih Atici , Hongyi Pan , Ahmet Enis Cetin

Gradient clipping is a standard safeguard for training neural networks under noisy, heavy-tailed stochastic gradients; yet, most clipping rules treat all parameters as vectors and ignore the matrix structure of modern architectures. We show…

Machine Learning · Computer Science 2026-05-13 Alexander Yukhimchuk , Mladen Kolar , Martin Takáč , Sayantan Choudhury

Spiking neural networks (SNNs) well support spatiotemporal learning and energy-efficient event-driven hardware neuromorphic processors. As an important class of SNNs, recurrent spiking neural networks (RSNNs) possess great computational…

Neural and Evolutionary Computing · Computer Science 2020-02-25 Wenrui Zhang , Peng Li

Layer normalization (LayerNorm) has been successfully applied to various deep neural networks to help stabilize training and boost model convergence because of its capability in handling re-centering and re-scaling of both inputs and weight…

Machine Learning · Computer Science 2019-10-17 Biao Zhang , Rico Sennrich

Modern meta-learning approaches for image classification rely on increasingly deep networks to achieve state-of-the-art performance, making batch normalization an essential component of meta-learning pipelines. However, the hierarchical…

Machine Learning · Statistics 2020-07-14 John Bronskill , Jonathan Gordon , James Requeima , Sebastian Nowozin , Richard E. Turner

Building on our prior explorations of convolutional neural networks (CNNs) for financial data processing, this paper introduces two significant enhancements to refine our CNN model's predictive performance and robustness for financial…

Computational Finance · Quantitative Finance 2024-08-23 Sina Montazeri , Haseebullah Jumakhan , Sonia Abrasiabian , Amir Mirzaeinia