English
Related papers

Related papers: Tailor: Altering Skip Connections for Resource-Eff…

200 papers

On-device training enables the model to adapt to new data collected from the sensors by fine-tuning a pre-trained model. Users can benefit from customized AI models without having to transfer the data to the cloud, protecting the privacy.…

Computer Vision and Pattern Recognition · Computer Science 2024-04-04 Ji Lin , Ligeng Zhu , Wei-Ming Chen , Wei-Chen Wang , Chuang Gan , Song Han

Recent studies have shown that skeletonization (pruning parameters) of networks \textit{at initialization} provides all the practical benefits of sparsity both at inference and training time, while only marginally degrading their…

Computer Vision and Pattern Recognition · Computer Science 2021-03-22 Pau de Jorge , Amartya Sanyal , Harkirat S. Behl , Philip H. S. Torr , Gregory Rogez , Puneet K. Dokania

Addressing the challenge of data scarcity in industrial domains, transfer learning emerges as a pivotal paradigm. This work introduces Style Filter, a tailored methodology for industrial contexts. By selectively filtering source domain data…

Machine Learning · Computer Science 2024-03-26 Chen Li , Ruijie Ma , Xiang Qian , Xiaohao Wang , Xinghui Li

Fault-tolerant deep learning accelerator is the basis for highly reliable deep learning processing and critical to deploy deep learning in safety-critical applications such as avionics and robotics. Since deep learning is known to be…

Hardware Architecture · Computer Science 2023-12-22 Qing Zhang , Cheng Liu , Bo Liu , Haitong Huang , Ying Wang , Huawei Li , Xiaowei Li

Hardware-based neuromorphic computing remains an elusive goal with the potential to profoundly impact future technologies and deepen our understanding of emergent intelligence. The learning-from-mistakes algorithm is one of the few training…

Disordered Systems and Neural Networks · Physics 2025-06-23 Frank Barrows , Jonathan Lin , Francesco Caravelli , Dante R. Chialvo

Deep Neural Networks (DNNs) on hardware is facing excessive computation cost due to the massive number of parameters. A typical training pipeline to mitigate over-parameterization is to pre-define a DNN structure first with redundant…

Neural and Evolutionary Computing · Computer Science 2019-12-19 Xiaocong Du , Zheng Li , Yufei Ma , Yu Cao

Advanced deep neural networks (DNNs), designed by either human or AutoML algorithms, are growing increasingly complex. Diverse operations are connected by complicated connectivity patterns, e.g., various types of skip connections. Those…

Machine Learning · Computer Science 2022-10-13 Wuyang Chen , Wei Huang , Xinyu Gong , Boris Hanin , Zhangyang Wang

This paper presents an iterative pruning strategy for Convolutional Network Fabrics (CNF) in presence of noisy training and testing data. With the continuous increase in size of neural network models, various authors have developed pruning…

Machine Learning · Computer Science 2022-02-16 Ilias Benjelloun , Bart Lamiroy , Efoevi Koudou

The rapid growth of deep learning models has increased the demand for efficient distributed training strategies. Fully sharded approaches like ZeRO-3 and FSDP partition model parameters across GPUs and apply optimizations such as…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-02-20 Masahiro Tanaka , Du Li , Umesh Chand , Ali Zafar , Haiying Shen , Olatunji Ruwase

Time-To-First-Spike (TTFS) coding in Spiking Neural Networks (SNNs) offers significant advantages in terms of energy efficiency, closely mimicking the behavior of biological neurons. In this work, we delve into the role of skip connections,…

Signal Processing · Electrical Eng. & Systems 2023-12-05 Youngeun Kim , Adar Kahana , Ruokai Yin , Yuhang Li , Panos Stinis , George Em Karniadakis , Priyadarshini Panda

Deep neural networks (DNNs) are nowadays witnessing a major success in solving many pattern recognition tasks including skeleton-based classification. The deployment of DNNs on edge-devices, endowed with limited time and memory resources,…

Computer Vision and Pattern Recognition · Computer Science 2024-12-17 Hichem Sahbi

Understanding whether deep neural networks are effectively optimized remains challenging, as training occurs in highly nonconvex landscapes and standard metrics provide limited visibility into layer-wise learning quality. This challenge is…

Machine Learning · Computer Science 2026-05-05 Arian Eamaz , Farhang Yeganegi , Mojtaba Soltanalian

Transformer-based models, such as BERT and ViT, have achieved state-of-the-art results across different natural language processing (NLP) and computer vision (CV) tasks. However, these models are extremely memory intensive during their…

Computation and Language · Computer Science 2023-05-31 Arash Ardakani , Altan Haan , Shangyin Tan , Doru Thom Popovici , Alvin Cheung , Costin Iancu , Koushik Sen

While GPUs are responsible for training the vast majority of state-of-the-art deep learning models, the implications of their architecture are often overlooked when designing new deep learning (DL) models. As a consequence, modifying a DL…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-02-01 Quentin Anthony , Jacob Hatef , Deepak Narayanan , Stella Biderman , Stas Bekman , Junqi Yin , Aamir Shafi , Hari Subramoni , Dhabaleswar Panda

With an ever-growing number of parameters defining increasingly complex networks, Deep Learning has led to several breakthroughs surpassing human performance. As a result, data movement for these millions of model parameters causes a…

Neural and Evolutionary Computing · Computer Science 2023-04-12 Christopher Wolters , Brady Taylor , Edward Hanson , Xiaoxuan Yang , Ulf Schlichtmann , Yiran Chen

In this work, we study to release the potential of massive heterogeneous weak computing power to collaboratively train large-scale models on dispersed datasets. In order to improve both efficiency and accuracy in resource-adaptive…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-10-24 Yan Li , Xiao Zhang , Mingyi Li , Guangwei Xu , Feng Chen , Yuan Yuan , Yifei Zou , Mengying Zhao , Jianbo Lu , Dongxiao Yu

We consider using deep neural networks to solve time-dependent partial differential equations (PDEs), where multi-scale processing is crucial for modeling complex, time-evolving dynamics. While the U-Net architecture with skip connections…

Machine Learning · Computer Science 2024-03-29 Xuan Zhang , Jacob Helwig , Yuchao Lin , Yaochen Xie , Cong Fu , Stephan Wojtowytsch , Shuiwang Ji

Deep Neural Networks (DNNs) are usually over-parameterized, causing excessive memory and interconnection cost on the hardware platform. Existing pruning approaches remove secondary parameters at the end of training to reduce the model size;…

Machine Learning · Computer Science 2019-11-12 Gokul Krishnan , Xiaocong Du , Yu Cao

In the world of deep learning, Transformer models have become very significant, leading to improvements in many areas from understanding language to recognizing images, covering a wide range of applications. Despite their success, the…

Machine Learning · Computer Science 2024-07-19 Ghadeer Jaradat , Mohammed Tolba , Ghada Alsuhli , Hani Saleh , Mahmoud Al-Qutayri , Thanos Stouraitis , Baker Mohammad

Deep learning fostered a leap ahead in automated skin lesion analysis in the last two years. Those models are expensive to train and difficult to parameterize. Objective: We investigate methodological issues for designing and evaluating…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Eduardo Valle , Michel Fornaciali , Afonso Menegola , Julia Tavares , Flávia Vasques Bittencourt , Lin Tzy Li , Sandra Avila