English
Related papers

Related papers: Bayesian Compression for Deep Learning

200 papers

Compression techniques for deep neural networks are important for implementing them on small embedded devices. In particular, channel-pruning is a useful technique for realizing compact networks. However, many conventional methods require…

Machine Learning · Statistics 2021-11-03 Kohei Yamamoto , Kurato Maeno

EIE proposed to accelerate pruned and compressed neural networks, exploiting weight sparsity, activation sparsity, and 4-bit weight-sharing in neural network accelerators. Since published in ISCA'16, it opened a new design space to…

Hardware Architecture · Computer Science 2023-06-19 Song Han , Xingyu Liu , Huizi Mao , Jing Pu , Ardavan Pedram , Mark A. Horowitz , William J. Dally

This paper proposes a sparse Bayesian treatment of deep neural networks (DNNs) for system identification. Although DNNs show impressive approximation ability in various fields, several challenges still exist for system identification…

Systems and Control · Electrical Eng. & Systems 2022-06-02 Hongpeng Zhou , Chahine Ibrahim , Wei Xing Zheng , Wei Pan

In natural language processing, a lot of the tasks are successfully solved with recurrent neural networks, but such models have a huge number of parameters. The majority of these parameters are often concentrated in the embedding layer,…

Computation and Language · Computer Science 2018-12-13 Nadezhda Chirkova , Ekaterina Lobacheva , Dmitry Vetrov

Deep neural networks have been the predominant paradigm in machine learning for solving cognitive tasks. Such models, however, are restricted by a high computational overhead, limiting their applicability and hindering advancements in the…

Machine Learning · Computer Science 2024-11-05 Ian Pons , Bruno Yamamoto , Anna H. Reali Costa , Artur Jordao

Bayesian neural networks (BNNs) augment deep networks with uncertainty quantification by Bayesian treatment of the network weights. However, such models face the challenge of Bayesian inference in a high-dimensional and usually…

Machine Learning · Computer Science 2021-03-30 Zhijie Deng , Yucen Luo , Jun Zhu , Bo Zhang

Recent advances in deep learning have made available large, powerful convolutional neural networks (CNN) with state-of-the-art performance in several real-world applications. Unfortunately, these large-sized models have millions of…

Machine Learning · Computer Science 2020-07-17 Giosuè Cataldo Marinò , Gregorio Ghidoli , Marco Frasca , Dario Malchiodi

Deep neural networks are powerful, yet their high complexity greatly limits their potential to be deployed on billions of resource-constrained edge devices. Pruning is a crucial network compression technique, yet most existing methods focus…

Computer Vision and Pattern Recognition · Computer Science 2025-09-23 Qizhen Lan , Jung Im Choi , Qing Tian

Deep learning approaches have achieved unprecedented performance in visual recognition tasks such as object detection and pose estimation. However, state-of-the-art models have millions of parameters represented as floats which make them…

Computer Vision and Pattern Recognition · Computer Science 2021-02-08 Gedeon Muhawenayo , Georgia Gkioxari

Many contemporary machine learning models require extensive tuning of hyperparameters to perform well. A variety of methods, such as Bayesian optimization, have been developed to automate and expedite this process. However, tuning remains…

Machine Learning · Computer Science 2020-02-25 Setareh Ariafar , Zelda Mariet , Ehsan Elhamifar , Dana Brooks , Jennifer Dy , Jasper Snoek

Quantization and pruning are core techniques used to reduce the inference costs of deep neural networks. State-of-the-art quantization techniques are currently applied to both the weights and activations; however, pruning is most often…

Machine Learning · Computer Science 2021-11-02 Xinyu Zhang , Ian Colbert , Ken Kreutz-Delgado , Srinjoy Das

Significant success has been reported recently using deep neural networks for classification. Such large networks can be computationally intensive, even after training is over. Implementing these trained networks in hardware chips with a…

Machine Learning · Statistics 2013-10-25 Daniel Soudry , Ron Meir

We consider the problem of robust compressed sensing whose objective is to recover a high-dimensional sparse signal from compressed measurements corrupted by outliers. A new sparse Bayesian learning method is developed for robust compressed…

Machine Learning · Statistics 2016-10-24 Qian Wan , Huiping Duan , Jun Fang , Hongbin Li

Bayesian methods in machine learning, such as Gaussian processes, have great advantages com-pared to other techniques. In particular, they provide estimates of the uncertainty associated with a prediction. Extending the Bayesian approach to…

Quantum Physics · Physics 2019-05-20 Zhikuan Zhao , Alejandro Pozas-Kerstjens , Patrick Rebentrost , Peter Wittek

Compression techniques for deep neural network models are becoming very important for the efficient execution of high-performance deep learning systems on edge-computing devices. The concept of model compression is also important for…

Deep ensembles have emerged as a powerful technique for improving predictive performance and enhancing model robustness across various applications by leveraging model diversity. However, traditional deep ensemble methods are often…

Introduced in the late 1980s for generalization purposes, pruning has now become a staple for compressing deep neural networks. Despite many innovations in recent decades, pruning approaches still face core issues that hinder their…

Neural and Evolutionary Computing · Computer Science 2022-03-10 Hugo Tessier , Vincent Gripon , Mathieu Léonardon , Matthieu Arzel , Thomas Hannagan , David Bertrand

Dictionary learning methods continue to gain popularity for the solution of challenging inverse problems. In the dictionary learning approach, the computational forward model is replaced by a large dictionary of possible outcomes, and the…

Machine Learning · Statistics 2023-09-06 Alberto Bocchinfuso , Daniela Calvetti , Erkki Somersalo

The goal of model compression is to reduce the size of a large neural network while retaining a comparable performance. As a result, computation and memory costs in resource-limited applications may be significantly reduced by dropping…

Machine Learning · Statistics 2022-11-10 Wenjing Yang , Ganghua Wang , Jie Ding , Yuhong Yang

Deep learning is increasingly moving towards a transfer learning paradigm whereby large foundation models are fine-tuned on downstream tasks, starting from an initialization learned on the source task. But an initialization contains…

Machine Learning · Computer Science 2022-05-23 Ravid Shwartz-Ziv , Micah Goldblum , Hossein Souri , Sanyam Kapoor , Chen Zhu , Yann LeCun , Andrew Gordon Wilson