Neural Network

Neural networks are computational models inspired by the structure and function of the brain, primarily aimed at approximating complex functions and solving diverse problems through learning from data. Current research emphasizes improving efficiency and robustness, exploring novel architectures like sinusoidal neural fields and hybrid models combining neural networks with radial basis functions, as well as developing methods for understanding and manipulating the internal representations learned by these networks, such as through hyper-representations of network weights. These advancements are driving progress in various fields, including computer vision, natural language processing, and scientific modeling, by enabling more accurate, efficient, and interpretable AI systems.

Papers

October 30, 2024

Tightening convex relaxations of trained neural networks: a unified approach for convex and S-shaped activations
Pablo Carrasco, Gonzalo Muñoz
Neural Network Constructive Approach Convex Relaxation Convex Machine Learning Convex Approximation
Why Fine-grained Labels in Pretraining Benefit Generalization?
Guan Zhe Hong, Yin Cui, Ariel Fuxman, Stanley Chan, Enming Luo
Neural Network Deep Neural Network Fine Grained Label Information Better Generalization Generalization Benefit Coarse Label

October 29, 2024

Vertical Federated Learning with Missing Features During Training and Inference
Pedro Valdeira, Shiqiang Wang, Yuejie Chi
Neural Network Training Data Scientific Inference Efficient Training Vertical Federated Learning Non Convex Objective
Towards Neural-Network-based optical temperature sensing of Semiconductor Membrane External Cavity Laser
Jakob Mannstadt, Arash Rahimi-Iman
Neural Network High Power Laser Semiconductor Laser Raman Amplifier
Task-Oriented Real-time Visual Inference for IoVT Systems: A Co-design Framework of Neural Networks and Edge Deployment
Jiaqi Wu, Simin Chen, Zehua Wang, Wei Chen, Zijian Tian, F. Richard Yu, Victor C. M. Leung
Neural Network New Framework Neural Architecture Search Supervised ImageNet Real Time Inference Edge Deployment Performing Model
Drone Acoustic Analysis for Predicting Psychoacoustic Annoyance via Artificial Neural Networks
Andrea Vaiuso, Marcello Righi, Oier Coretti, Moreno Apicella
Neural Network Unmanned Aerial Vehicle Drone Dataset
Where Do Large Learning Rates Lead Us?
Ildus Sadrtdinov, Maxim Kodryan, Eduard Pokonechny, Ekaterina Lobacheva, Dmitry Vetrov
Neural Network Strong Generalization Optimization Purpose Learning Rate Large Learning Rate
Flavors of Margin: Implicit Bias of Steepest Descent in Homogeneous Neural Networks
Nikolaos Tsilivis, Gal Vardi, Julia Kempe
Neural Network Gradient Descent Implicit Bias Margin Maximization Homogeneity Bias Systematic Bias Homogeneous Neural Network
Bayesian Optimization for Hyperparameters Tuning in Neural Networks
Gabriele Onorato
Neural Network Bayesian Optimization Hyperparameter Tuning Derivative Free Optimization
Machine Unlearning using Forgetting Neural Networks
Amartya Hatua, Trung T. Nguyen, Filip Cano, Andrew H. Sung
Neural Network Anti Forgetting Machine Unlearning Unlearning Framework Unlearned Model Human Memory
Predicting the Encoding Error of SIRENs
Jeremy Vonderfecht, Feng Liu
Neural Network Data Encoding Audio Compression Hi Lo SIReN

October 28, 2024

Audio Classification of Low Feature Spectrograms Utilizing Convolutional Neural Networks
Noel Elias
Neural Network Deep Convolutional Neural Network Audio Classification Audio Spectrogram Spectral Signature Frequency Representation
Super-resolution in disordered media using neural networks
Alexander Christie, Matan Leibovich, Miguel Moscoso, Alexei Novikov, George Papanicolaou, Chrysoula Tsogka
Neural Network Super Resolution Ethnic Medium Homogeneity Bias Ambient Sound Sub Aperture Image
Inverting Gradient Attacks Makes Powerful Data Poisoning
Wassim Bouaziz, El-Mahdi El-Mhamdi, Nicolas Usunier
Neural Network Data Poisoning Gradient Inversion Attack Gradient Based Attack Resource Utilization Gradient Attack Availability Attack
Modular Duality in Deep Learning
Jeremy Bernstein, Laker Newhouse
Neural Network Deep Learning Neural Architecture Strong Duality Dual Formulation
LAMA: Stable Dual-Domain Deep Reconstruction For Sparse-View CT
Chi Ding, Qingchao Zhang, Ge Wang, Xiaojing Ye, Yunmei Chen
Neural Network Inverse Problem Sparse View Alternating Minimization Dual Domain Reconstruction
NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks
Yongchang Hao, Yanshuai Cao, Lili Mou
Neural Network Scientific Inference Memory Efficient Training Memory Capacity Lossless Performance

October 26, 2024

Analyzing Multi-Stage Loss Curve: Plateau and Descent Mechanisms in Neural Networks
Zheng-An Chen, Tao Luo, GuiHong Wang
Neural Network Training Dynamic Early Stage Descent Property
Self-Normalized Resets for Plasticity in Continual Learning
Vivek F. Farias, Adam D. Jozefiak
Neural Network Continual LEArning Continual Learning Plasticity Rule Global Reset Feature Plasticity Loss Based Reset
Evaluating Neural Networks for Early Maritime Threat Detection
Dhanush Tella, Chandra Teja Tiriveedhi, Naphtali Rishe, Dan E. Tamir, Jonathan I. Tamir
Neural Network Deep Network Maritime Surveillance Neural Method Discriminative Clustering

Neural Network

Papers

Tightening convex relaxations of trained neural networks: a unified approach for convex and S-shaped activations

Why Fine-grained Labels in Pretraining Benefit Generalization?

Vertical Federated Learning with Missing Features During Training and Inference

Towards Neural-Network-based optical temperature sensing of Semiconductor Membrane External Cavity Laser

Task-Oriented Real-time Visual Inference for IoVT Systems: A Co-design Framework of Neural Networks and Edge Deployment

Drone Acoustic Analysis for Predicting Psychoacoustic Annoyance via Artificial Neural Networks

Where Do Large Learning Rates Lead Us?

Flavors of Margin: Implicit Bias of Steepest Descent in Homogeneous Neural Networks

Bayesian Optimization for Hyperparameters Tuning in Neural Networks

Machine Unlearning using Forgetting Neural Networks

Predicting the Encoding Error of SIRENs

Audio Classification of Low Feature Spectrograms Utilizing Convolutional Neural Networks

Super-resolution in disordered media using neural networks

Inverting Gradient Attacks Makes Powerful Data Poisoning

Modular Duality in Deep Learning

LAMA: Stable Dual-Domain Deep Reconstruction For Sparse-View CT

NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks

Analyzing Multi-Stage Loss Curve: Plateau and Descent Mechanisms in Neural Networks

Self-Normalized Resets for Plasticity in Continual Learning

Evaluating Neural Networks for Early Maritime Threat Detection