English
Related papers

Related papers: Universally Slimmable Networks and Improved Traini…

200 papers

Residual networks have shown great success and become indispensable in recent deep neural network models. In this work, we aim to re-investigate the training process of residual networks from a novel social psychology perspective of…

Machine Learning · Computer Science 2023-05-05 Peng Ye , Tong He , Shengji Tang , Baopu Li , Tao Chen , Lei Bai , Wanli Ouyang

We propose a general method to train a single convolutional neural network which is capable of switching image resolutions at inference. Thus the running speed can be selected to meet various computational resource limits. Networks trained…

Computer Vision and Pattern Recognition · Computer Science 2020-11-10 Yikai Wang , Fuchun Sun , Duo Li , Anbang Yao

Graph Neural Networks (GNNs) are widely applied to graph learning problems such as node classification. When scaling up the underlying graphs of GNNs to a larger size, we are forced to either train on the complete graph and keep the full…

Machine Learning · Computer Science 2024-06-25 Mucong Ding , Tahseen Rabbani , Bang An , Evan Z Wang , Furong Huang

Optimizing the channel counts for different layers of a CNN has shown great promise in improving the efficiency of CNNs at test-time. However, these methods often introduce large computational overhead (e.g., an additional 2x FLOPs of…

Computer Vision and Pattern Recognition · Computer Science 2021-04-28 Ting-Wu Chin , Diana Marculescu , Ari S. Morcos

One-shot Neural architecture search (One-shot NAS) has been proposed as a time-efficient approach to obtain optimal subnet architectures and weights under different complexity cases by training only once. However, the subnet performance…

Computer Vision and Pattern Recognition · Computer Science 2023-07-18 Mingyang Zhang , Xinyi Yu , Haodong Zhao , Linlin Ou

We present any-precision deep neural networks (DNNs), which are trained with a new method that allows the learned DNNs to be flexible in numerical precision during inference. The same model in runtime can be flexibly and directly set to…

Machine Learning · Computer Science 2021-01-18 Haichao Yu , Haoxiang Li , Honghui Shi , Thomas S. Huang , Gang Hua

In general, deep neural network (DNN) pruning methods fall into two categories: 1) Weight-based deterministic constraints, and 2) Probabilistic frameworks. While each approach has its merits and limitations there are a set of common…

Computer Vision and Pattern Recognition · Computer Science 2021-12-21 Madan Ravi Ganesh , Dawsin Blanchard , Jason J. Corso , Salimeh Yasaei Sekeh

U-Net, known for its simple yet efficient architecture, is widely utilized for image processing tasks and is particularly suitable for deployment on neuromorphic chips. This paper introduces the novel concept of Spiking-UNet for image…

Neural and Evolutionary Computing · Computer Science 2024-04-12 Hebei Li , Yueyi Zhang , Zhiwei Xiong , Xiaoyan Sun

MobileNet and Binary Neural Networks are two among the most widely used techniques to construct deep learning models for performing a variety of tasks on mobile and embedded platforms.In this paper, we present a simple yet efficient scheme…

Computer Vision and Pattern Recognition · Computer Science 2019-08-01 Hai Phan , Dang Huynh , Yihui He , Marios Savvides , Zhiqiang Shen

Monotonicity constraints are powerful regularizers in statistical modelling. They can support fairness in computer-aided decision making and increase plausibility in data-driven scientific models. The seminal min-max (MM) neural network…

Machine Learning · Computer Science 2024-05-28 Christian Igel

Network reliability is an important metric to evaluate the connectivity among given vertices in uncertain graphs. Since the network reliability problem is known as #P-complete, existing studies have used approximation techniques. In this…

Data Structures and Algorithms · Computer Science 2020-09-08 Yuya Sasaki , Yasuhiro Fujiwara , Makoto Onizuka

Neural networks are often over-parameterized and hence benefit from aggressive regularization. Conventional regularization methods, such as Dropout or weight decay, do not leverage the structures of the network's inputs and hidden states.…

Machine Learning · Computer Science 2021-01-07 Hieu Pham , Quoc V. Le

Deep neural networks (DNNs) and Kolmogorov-Arnold networks (KANs) are popular methods for function approximation due to their flexibility and expressivity. However, they typically require a large number of trainable parameters to produce a…

Machine Learning · Computer Science 2025-11-27 Zachary Morrow , Michael Penwarden , Brian Chen , Aurya Javeed , Akil Narayan , John D. Jakeman

Deep neural networks tend to underestimate uncertainty and produce overly confident predictions. Recently proposed solutions, such as MC Dropout and SDENet, require complex training and/or auxiliary out-of-distribution data. We propose a…

Machine Learning · Computer Science 2021-10-14 Akib Mashrur , Wei Luo , Nayyar A. Zaidi , Antonio Robles-Kelly

In neural networks, the property of being equivariant to transformations improves generalization when the corresponding symmetry is present in the data. In particular, scale-equivariant networks are suited to computer vision tasks where the…

Machine Learning · Statistics 2022-10-11 Mateus Sangalli , Samy Blusseau , Santiago Velasco-Forero , Jesus Angulo

Spiking Neural Networks (SNNs) emerged as a promising solution in the field of Artificial Neural Networks (ANNs), attracting the attention of researchers due to their ability to mimic the human brain and process complex information with…

Neural and Evolutionary Computing · Computer Science 2023-09-12 Pavithra Koralalage , Ireoluwa Fakeye , Pedro Machado , Jason Smith , Isibor Kennedy Ihianle , Salisu Wada Yahaya , Andreas Oikonomou , Ahmad Lotfi

We propose self-adaptive training -- a unified training algorithm that dynamically calibrates and enhances training processes by model predictions without incurring an extra computational cost -- to advance both supervised and…

Machine Learning · Computer Science 2022-10-17 Lang Huang , Chao Zhang , Hongyang Zhang

We introduce a flexible setup allowing for a neural network to learn both its size and topology during the course of a standard gradient-based training. The resulting network has the structure of a graph tailored to the particular learning…

Machine Learning · Computer Science 2020-07-16 Romuald A. Janik , Aleksandra Nowak

This paper tackles the problem of training a deep convolutional neural network with both low-precision weights and low-bitwidth activations. Optimizing a low-precision network is very challenging since the training process can easily get…

Computer Vision and Pattern Recognition · Computer Science 2021-06-05 Bohan Zhuang , Chunhua Shen , Mingkui Tan , Lingqiao Liu , Ian Reid

Many imaging tasks require global information about all pixels in an image. Conventional bottom-up classification networks globalize information by decreasing resolution; features are pooled and downsampled into a single output. But for…

Computer Vision and Pattern Recognition · Computer Science 2018-04-30 Sohil Shah , Pallabi Ghosh , Larry S Davis , Tom Goldstein
‹ Prev 1 3 4 5 6 7 10 Next ›