中文
相关论文

相关论文: Heterogeneous Connectivity in Sparse Networks: Fan…

200 篇论文

Neural network forms the foundation of deep learning and numerous AI applications. Classical neural networks are fully connected, expensive to train and prone to overfitting. Sparse networks tend to have convoluted structure search,…

机器学习 · 计算机科学 2020-12-03 Weijun Luo

Spiking Neural Networks (SNNs) represent the forefront of neuromorphic computing, promising energy-efficient and biologically plausible models for complex tasks. This paper weaves together three groundbreaking studies that revolutionize SNN…

神经与进化计算 · 计算机科学 2024-07-10 Biswadeep Chakraborty , Saibal Mukhopadhyay

Recurrent Spiking Neural Networks (RSNNs) have emerged as a computationally efficient and brain-inspired learning model. The design of sparse RSNNs with fewer neurons and synapses helps reduce the computational complexity of RSNNs.…

神经与进化计算 · 计算机科学 2024-03-07 Biswadeep Chakraborty , Beomseok Kang , Harshit Kumar , Saibal Mukhopadhyay

We propose Sparse Neural Network architectures that are based on random or structured bipartite graph topologies. Sparse architectures provide compression of the models learned and speed-ups of computations, they can also surpass their…

机器学习 · 计算机科学 2017-06-20 Alfred Bourely , John Patrick Boueri , Krzysztof Choromonski

Both biological and artificial neural networks inherently balance their performance with their operational cost, which balances their computational abilities. Typically, an efficient neuromorphic neural network is one that learns…

神经元与认知 · 定量生物学 2023-12-25 Hugo J. Ladret , Christian Casanova , Laurent Udo Perrinet

Identifying the structural priors that enable Deep Neural Networks (DNNs) to overcome the curse of dimensionality is a fundamental challenge in machine learning theory. Existing literature suggests that effective high-dimensional learning…

机器学习 · 计算机科学 2026-05-15 Hongyu Lin , Antonio Briola , Yuanrong Wang , Tomaso Aste

Graphical modelling techniques based on sparse selection have been applied to infer complex networks in many fields, including biology and medicine, engineering, finance, and social sciences. One structural feature of some of the networks…

统计理论 · 数学 2020-03-03 Annaliza McGillivray , Abbas Khalili , David A. Stephens

Gradient descent on overparameterized neural networks typically operates at the Edge of Stability (EoS), where the largest Hessian eigenvalue hovers around a step-size-dependent threshold. We study how sparse connectivity changes…

机器学习 · 统计学 2026-05-08 Tongtong Liang , Esha Singh , Rahul Parhi , Alexander Cloninger , Yu-Xiang Wang

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…

神经与进化计算 · 计算机科学 2023-06-07 Jiangrong Shen , Qi Xu , Jian K. Liu , Yueming Wang , Gang Pan , Huajin Tang

It has been argued by Thom and Palm that sparsely-connected neural networks (SCNs) show improved performance over fully-connected networks (FCNs). Super-regular networks (SRNs) are neural networks composed of a set of stacked sparse layers…

机器学习 · 计算机科学 2022-01-06 Andrew W. E. McDonald , Ali Shokoufandeh

Low precision weights, activations, and gradients have been proposed as a way to improve the computational efficiency and memory footprint of deep neural networks. Recently, low precision networks have even shown to be more robust to…

机器学习 · 计算机科学 2018-07-04 Griffin Lacey , Graham W. Taylor , Shawki Areibi

Sparse Neural Networks (SNNs) can potentially demonstrate similar performance to their dense counterparts while saving significant energy and memory at inference. However, the accuracy drop incurred by SNNs, especially at high pruning…

机器学习 · 计算机科学 2023-06-06 Mohammad Loni , Aditya Mohan , Mehdi Asadi , Marius Lindauer

Effectively scaling up deep reinforcement learning models has proven notoriously difficult due to network pathologies during training, motivating various targeted interventions such as periodic reset and architectural advances such as layer…

机器学习 · 计算机科学 2025-06-23 Guozheng Ma , Lu Li , Zilin Wang , Li Shen , Pierre-Luc Bacon , Dacheng Tao

We introduce Resonant Sparse Geometry Networks (RSGN), a brain-inspired architecture with self-organizing sparse hierarchical input-dependent connectivity. Unlike Transformer architectures that employ dense attention mechanisms with O(n^2)…

机器学习 · 计算机科学 2026-01-27 Hasi Hays

Sparse deep neural networks(DNNs) are efficient in both memory and compute when compared to dense DNNs. But due to irregularity in computation of sparse DNNs, their efficiencies are much lower than that of dense DNNs on regular parallel…

机器学习 · 计算机科学 2018-12-31 Dharma Teja Vooturi , Dheevatsa Mudigere , Sasikanth Avancha

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)…

神经与进化计算 · 计算机科学 2021-12-22 Minghai Qin , Tianyun Zhang , Fei Sun , Yen-Kuang Chen , Makan Fardad , Yanzhi Wang , Yuan Xie

Sparse Neural Networks (SNNs) have emerged as powerful tools for efficient feature selection. Leveraging the dynamic sparse training (DST) algorithms within SNNs has demonstrated promising feature selection capabilities while drastically…

Sparsity in Deep Neural Networks (DNNs) has been widely studied to compress and accelerate the models on resource-constrained environments. It can be generally categorized into unstructured fine-grained sparsity that zeroes out multiple…

计算机视觉与模式识别 · 计算机科学 2021-04-20 Aojun Zhou , Yukun Ma , Junnan Zhu , Jianbo Liu , Zhijie Zhang , Kun Yuan , Wenxiu Sun , Hongsheng Li

Sparse neural networks are effective approaches to reduce the resource requirements for the deployment of deep neural networks. Recently, the concept of adaptive sparse connectivity, has emerged to allow training sparse neural networks from…

Characterising the heterogeneous presentation of Parkinson's disease (PD) requires integrating biological and clinical markers within a unified predictive framework. While multimodal data provide complementary information, many existing…

机器学习 · 计算机科学 2026-01-05 Dristi Datta , Tanmoy Debnath , Minh Chau , Manoranjan Paul , Gourab Adhikary , Md Geaur Rahman
‹ 上一页 1 2 3 10 下一页 ›