English
Related papers

Related papers: Sparse Mutation Decompositions: Fine Tuning Deep N…

200 papers

While deep learning has demonstrated impressive progress, it remains a daunting challenge to learn from hard samples as these samples are usually noisy and intricate. These hard samples play a crucial role in the optimal performance of deep…

Computer Vision and Pattern Recognition · Computer Science 2024-12-30 Qiao Xiao , Boqian Wu , Lu Yin , Christopher Neil Gadzinski , Tianjin Huang , Mykola Pechenizkiy , Decebal Constantin Mocanu

Spiking neural networks (SNNs) have manifested remarkable advantages in power consumption and event-driven property during the inference process. To take full advantage of low power consumption and improve the efficiency of these models…

Neural and Evolutionary Computing · Computer Science 2023-06-07 Jiangrong Shen , Qi Xu , Jian K. Liu , Yueming Wang , Gang Pan , Huajin Tang

Deep neural networks (DNNs) have shown to provide superb performance in many real life applications, but their large computation cost and storage requirement have prevented them from being deployed to many edge and internet-of-things (IoT)…

Neural and Evolutionary Computing · Computer Science 2021-12-22 Minghai Qin , Tianyun Zhang , Fei Sun , Yen-Kuang Chen , Makan Fardad , Yanzhi Wang , Yuan Xie

During typical gradient-based training of deep neural networks, all of the model's parameters are updated at each iteration. Recent work has shown that it is possible to update only a small subset of the model's parameters during training,…

Machine Learning · Computer Science 2021-11-19 Yi-Lin Sung , Varun Nair , Colin Raffel

Generative graph models struggle to scale due to the need to predict the existence or type of edges between all node pairs. To address the resulting quadratic complexity, existing scalable models often impose restrictive assumptions such as…

Machine Learning · Computer Science 2024-05-24 Yiming Qin , Clement Vignac , Pascal Frossard

Conventional deep network training generally optimizes all samples under a largely uniform learning paradigm, without explicitly modeling the heterogeneous competition among them. Such an oversimplified treatment can lead to several…

Computer Vision and Pattern Recognition · Computer Science 2026-04-15 Ying Zheng , Yiyi Zhang , Yi Wang , Lap-Pui Chau

In NeuroEvolution, the topologies of artificial neural networks are optimized with evolutionary algorithms to solve tasks in data regression, data classification, or reinforcement learning. One downside of NeuroEvolution is the large amount…

Neural and Evolutionary Computing · Computer Science 2019-02-12 Jörg Stork , Martin Zaefferer , Thomas Bartz-Beielstein

We introduce a sparse scattering deep convolutional neural network, which provides a simple model to analyze properties of deep representation learning for classification. Learning a single dictionary matrix with a classifier yields a…

Machine Learning · Computer Science 2020-02-21 John Zarka , Louis Thiry , Tomás Angles , Stéphane Mallat

In contrast to conventional artificial neural networks, which are structurally static, we present two approaches for evolving small networks into larger ones during training. The first method employs an auxiliary weight that directly…

Machine Learning · Computer Science 2025-07-29 Anil Radhakrishnan , John F. Lindner , Scott T. Miller , Sudeshna Sinha , William L. Ditto

Dynamic Sparse Training (DST) methods train neural networks by maintaining sparsity while dynamically adapting the network topology. Despite the promise of reduced computation, DST methods converge significantly slower than dense training,…

Machine Learning · Computer Science 2026-05-28 Mohammed Adnan , Rohan Jain , Tom Jacobs , Ekansh Sharma , Rahul G. Krishnan , Rebekka Burkholz , Yani Ioannou

We propose an image deconvolution algorithm when the data is contaminated by Poisson noise. The image to restore is assumed to be sparsely represented in a dictionary of waveforms such as the wavelet or curvelet transform. Our key…

Optimization and Control · Mathematics 2008-03-25 François-Xavier Dupé , Jalal Fadili , Jean Luc Starck

We consider a simple setting in neuroevolution where an evolutionary algorithm optimizes the weights and activation functions of a simple artificial neural network. We then define simple example functions to be learned by the network and…

Neural and Evolutionary Computing · Computer Science 2023-10-17 Paul Fischer , Emil Lundt Larsen , Carsten Witt

Understanding how information is represented in neural networks is a fundamental challenge in both neuroscience and artificial intelligence. Despite their nonlinear architectures, recent evidence suggests that neural networks encode…

Machine Learning · Computer Science 2025-03-04 David Klindt , Charles O'Neill , Patrik Reizinger , Harald Maurer , Nina Miolane

Recent work on deep neural network pruning has shown there exist sparse subnetworks that achieve equal or improved accuracy, training time, and loss using fewer network parameters when compared to their dense counterparts. Orthogonal to…

Machine Learning · Computer Science 2019-12-06 Justin Cosentino , Federico Zaiter , Dan Pei , Jun Zhu

Sparse expert models are a thirty-year old concept re-emerging as a popular architecture in deep learning. This class of architecture encompasses Mixture-of-Experts, Switch Transformers, Routing Networks, BASE layers, and others, all with…

Machine Learning · Computer Science 2022-09-07 William Fedus , Jeff Dean , Barret Zoph

Ultrasound imaging faces a trade-off between image quality and hardware complexity caused by dense transducers. Sparse arrays are one popular solution to mitigate this challenge. This work proposes an end-to-end optimization framework that…

Image and Video Processing · Electrical Eng. & Systems 2026-04-01 Sergio Urrea , Adrian Basarab , Hervé Liebgott , Henry Arguello

Deep neural networks have become very popular in modeling complex nonlinear processes due to their extraordinary ability to fit arbitrary nonlinear functions from data with minimal expert intervention. However, they are almost always…

Chemical Physics · Physics 2023-01-16 Erlend Torje Berg Lundby , Adil Rasheed , Ivar Johan Halvorsen , Jan Tommy Gravdahl

Despite the appeal of deep neural networks that largely replace the traditional handmade filters, they still suffer from isolated cases that cannot be properly handled only by the training of convolutional filters. Abnormal factors,…

Computer Vision and Pattern Recognition · Computer Science 2017-10-19 Jonghwa Yim , Kyung-Ah Sohn

We improve the recently developed Neural DUDE, a neural network-based adaptive discrete denoiser, by combining it with the supervised learning framework. Namely, we make the supervised pre-training of Neural DUDE compatible with the…

Machine Learning · Computer Science 2021-11-25 Sungmin Cha , Seonwoo Min , Sungroh Yoon , Taesup Moon

Multitask learning, i.e. learning several tasks at once with the same neural network, can improve performance in each of the tasks. Designing deep neural network architectures for multitask learning is a challenge: There are many ways to…

Neural and Evolutionary Computing · Computer Science 2018-04-19 Jason Liang , Elliot Meyerson , Risto Miikkulainen