Results 91 to 100 of about 36,322 (258)

Explaining the Origin of Negative Poisson's Ratio in Amorphous Networks With Machine Learning

Advanced Intelligent Discovery, EarlyView.
This review summarizes how machine learning (ML) breaks the “vicious cycle” in designing auxetic amorphous networks. By transitioning from traditional “black‐box” optimization to an interpretable “AI‐Physics” closed‐loop paradigm, ML is shown to not only discover highly optimized structures—such as all‐convex polygon networks—but also unveil hidden ...
Shengyu Lu, Xiangying Shen
wiley   +1 more source

Structure Optimization in Deep Neural Networks with Synaptic Pruning Based on Connection Appraisal [PDF]

Computer and Knowledge Engineering
Deep neural networks typically require predefined architectures, which can lead to overfitting, underfitting, high computational costs, and storage overhead.
Aghil Ahmadi, Reza Mahboobi Esfanjani
doaj   +1 more source

Rethinking Weight Decay for Efficient Neural Network Pruning. [PDF]

J Imaging, 2022
Tessier H, Gripon V, Léonardon M, Arzel M, Hannagan T, Bertrand D.   +5 more
europepmc   +1 more source

A Robust Deep Temporal Causal Discovery Platform for Single‐Cell Gene Regulatory Network Reconstruction

Advanced Intelligent Discovery, EarlyView.
scTIGER2.0 is a deep‐learning framework that infers gene regulatory networks from single‐cell RNA sequencing data. By integrating correlation, pseudotime ordering, deep learning and bootstrap‐based significance testing, it reduces false positives and reveals directional gene interactions.
Nishi Gupta, Madison Dautle, Shaoqiang Zhang, Yong Chen   +3 more
wiley   +1 more source

Differentiable Network Pruning via Polarization of Probabilistic Channelwise Soft Masks. [PDF]

Comput Intell Neurosci, 2022
Ma M, Wang J, Yu Z.
europepmc   +1 more source

A Breadth‐First Pruned‐Enriched Rosenbluth Method for Force–Extension Simulations of Confined Semiflexible Chains

Advanced Intelligent Discovery, EarlyView.
The behaviors of semiflexible polymers such as DNA and protein are often reshaped by coupled interactions. Monte Carlo simulations assist in studying these systems. This work recasts the traditional chain‐growth strategy into a new framework: a fixed number of chains grow synchronously, while less relevant chains to the target system are removed and ...
Yihan Zhao, Jizeng Wang
wiley   +1 more source

An automatic pruning method for SAR target detection based on multitask reinforcement learning

International Journal of Applied Earth Observations and Geoinformation
In recent years, research on synthetic aperture radar (SAR) target detection based on deep learning methods has made substantial progress in model accuracy.
Huiyao Wan, Jie Chen, Pazlat Nurmamat, Hongcheng Zeng, Wei Yang, Tao Xu, Bocai Wu, Jie Chen, Zhixiang Huang, Paulo S.R. Diniz   +9 more
doaj   +1 more source

Multi-Class Classification of Medical Data Based on Neural Network Pruning and Information-Entropy Measures. [PDF]

Entropy (Basel), 2022
Sánchez-Gutiérrez ME, González-Pérez PP.   +1 more
europepmc   +1 more source

Resource‐Aware Contrastive Scattering Meta‐Learning for Efficient Few‐Shot Acoustic Anomaly Detection

Advanced Intelligent Systems, EarlyView.
This paper introduces a resource‐aware Contrastive Scattering Meta‐Learning (CSML) framework for acoustic anomaly detection. By leveraging training‐free wavelet scattering and metric‐based meta‐learning, the model achieves competitive performance with only 50 K learnable parameters—a 98% reduction compared to state‐of‐the‐art frameworks—enabling ...
Rami Zewail, Bassem Mokhtar
wiley   +1 more source

Analog memristive synapse based on topotactic phase transition for high-performance neuromorphic computing and neural network pruning. [PDF]

Sci Adv, 2021
Mou X, Tang J, Lyu Y, Zhang Q, Yang S, Xu F, Liu W, Xu M, Zhou Y, Sun W, Zhong Y, Gao B, Yu P, Qian H, Wu H.   +14 more
europepmc   +1 more source