English
Related papers

Related papers: A Lightweight and Gradient-Stable Neural Layer

200 papers

Sparse neural networks are important for achieving better generalization and enhancing computation efficiency. This paper proposes a novel learning approach to obtain sparse fully connected layers in neural networks (NNs) automatically. We…

Machine Learning · Computer Science 2021-04-28 Mengqiao Han , Xiabi Liu , Zhaoyang Hai , Zhengwen Li

Systolic array accelerators execute CNNs with energy dominated by the switching activity of multiply accumulate (MAC) units. Although prior work exploits weight dependent MAC power for compression, existing methods often use global…

Hardware Architecture · Computer Science 2025-12-17 Jiaxun Fang , Grace Li Zhang , Shaoyi Huang

In this paper, we first identify activation shift, a simple but remarkable phenomenon in a neural network in which the preactivation value of a neuron has non-zero mean that depends on the angle between the weight vector of the neuron and…

Neural and Evolutionary Computing · Computer Science 2024-03-22 Takuro Kutsuna

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…

Graph Convolutional Networks (GCNs) and their variants have received significant attention and achieved start-of-the-art performances on various recommendation tasks. However, many existing GCN models tend to perform recursive aggregations…

Information Retrieval · Computer Science 2020-06-09 Yue Xu , Hao Chen , Zengde Deng , Junxiong Zhu , Yanghua Li , Peng He , Wenyao Gao , Wenjun Xu

Deep neural networks generally involve some layers with mil- lions of parameters, making them difficult to be deployed and updated on devices with limited resources such as mobile phones and other smart embedded systems. In this paper, we…

Computer Vision and Pattern Recognition · Computer Science 2016-08-29 Xing Wang , Jie Liang

In this paper we propose and study a technique to reduce the number of parameters and computation time in fully-connected layers of neural networks using Kronecker product, at a mild cost of the prediction quality. The technique proceeds by…

Neural and Evolutionary Computing · Computer Science 2015-07-23 Shuchang Zhou , Jia-Nan Wu

Standard neural networks are often overconfident when presented with data outside the training distribution. We introduce HyperGAN, a new generative model for learning a distribution of neural network parameters. HyperGAN does not require…

Machine Learning · Computer Science 2020-07-16 Neale Ratzlaff , Li Fuxin

In this paper, we propose in our novel generative framework the use of Generative Adversarial Networks (GANs) to generate features that provide robustness for object detection on reduced quality images. The proposed GAN-based Detection of…

Computer Vision and Pattern Recognition · Computer Science 2022-08-10 Charan D. Prakash , Lina J. Karam

The history of deep learning has shown that human-designed problem-specific networks can greatly improve the classification performance of general neural models. In most practical cases, however, choosing the optimal architecture for a…

Machine Learning · Computer Science 2020-09-14 Nicolo Colombo , Yang Gao

Physical Neural Networks (PNN) are promising platforms for next-generation computing systems. However, recent advances in digital neural network performance are largely driven by the rapid growth in the number of trainable parameters and,…

Machine Learning · Computer Science 2025-11-19 Kohei Tsuchiyama , Andre Roehm , Takatomo Mihana , Ryoichi Horisaki

Due to their high computational efficiency on a continuous space, gradient optimization methods have shown great potential in the neural architecture search (NAS) domain. The mapping of network representation from the discrete space to a…

Machine Learning · Computer Science 2020-06-20 Jian Li , Yong Liu , Jiankun Liu , Weiping Wang

Deep neural networks (DNNs) have achieved significant success in a variety of real world applications, i.e., image classification. However, tons of parameters in the networks restrict the efficiency of neural networks due to the large model…

Machine Learning · Computer Science 2019-08-21 Yuzhe Ma , Ran Chen , Wei Li , Fanhua Shang , Wenjian Yu , Minsik Cho , Bei Yu

Deep neural network models have a complex architecture and are overparameterized. The number of parameters is more than the whole dataset, which is highly resource-consuming. This complicates their application and limits its usage on…

Computer Vision and Pattern Recognition · Computer Science 2024-08-15 Vasiliy Alekseev , Ilya Lukashevich , Ilia Zharikov , Ilya Vasiliev

Despite much research, Graph Neural Networks (GNNs) still do not display the favorable scaling properties of other deep neural networks such as Convolutional Neural Networks and Transformers. Previous work has identified issues such as…

Machine Learning · Computer Science 2023-12-19 Ameen Ali , Hakan Cevikalp , Lior Wolf

We present a numerical scheme for computation of Artificial Neural Networks (ANN) weights, which stems from the Universal Approximation Theorem, avoiding laborious iterations. The proposed algorithm adheres to the underlying theory, is…

Machine Learning · Computer Science 2020-08-19 Nikolaos P. Bakas , Andreas Langousis , Mihalis Nicolaou , Savvas A. Chatzichristofis

Trainable layers such as convolutional building blocks are the standard network design choices by learning parameters to capture the global context through successive spatial operations. When designing an efficient network, trainable layers…

Computer Vision and Pattern Recognition · Computer Science 2022-03-22 Dongyoon Han , YoungJoon Yoo , Beomyoung Kim , Byeongho Heo

The recently proposed Kolmogorov-Arnold network (KAN) is a promising alternative to multi-layer perceptrons (MLPs) for data-driven modeling. While original KAN layers were only capable of representing the addition operator, the…

Machine Learning · Computer Science 2025-07-28 Benjamin C. Koenig , Suyong Kim , Sili Deng

Semi-supervised learning algorithms typically construct a weighted graph of data points to represent a manifold. However, an explicit graph representation is problematic for neural networks operating in the online setting. Here, we propose…

Machine Learning · Computer Science 2019-10-22 Alexander Genkin , Anirvan M. Sengupta , Dmitri Chklovskii

According to conventional neural network theories, the feature of single-hidden-layer feedforward neural networks(SLFNs) resorts to parameters of the weighted connections and hidden nodes. SLFNs are universal approximators when at least the…

Neural and Evolutionary Computing · Computer Science 2014-05-08 Yimin Yang , Q. M. Jonathan Wu , Guangbin Huang , Yaonan Wang