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

November 18, 2024

BALI: Learning Neural Networks via Bayesian Layerwise Inference
Richard Kurle, Alexej Klushyn, Ralf Herbrich
Neural Network Bayesian Neural Network Bayesian Perspective Covariance Matrix Bayesian Regression
A Neural Network Training Method Based on Distributed PID Control
Jiang Kun
Neural Network Differential Equation Proportional Integral Derivative Neural Network Framework
Don't Be So Positive: Negative Step Sizes in Second-Order Methods
Betty Shea, Mark Schmidt
Neural Network Hessian Matrix Second Order Step Size
Making Sigmoid-MSE Great Again: Output Reset Challenges Softmax Cross-Entropy in Neural Network Classification
Kanishka Tyagi, Chinmay Rane, Ketaki Vaidya, Jeshwanth Challgundla, Soumitro Swapan Auddy, Michael Manry
Neural Network Softmax Function Cross Entropy Sigmoid Function Neural Classifier Global Reset Feature Softmax Cross Entropy Classifier Robustness

November 17, 2024

Variational Bayesian Bow tie Neural Networks with Shrinkage
Alisa Sheinkman, Sara Wade
Neural Network Variational Inference Deep Model Bayesian Perspective Variational Bayesian Inference Shrinkage Estimator Exact Bayesian Inference
Distributed solar generation forecasting using attention-based deep neural networks for cloud movement prediction
Maneesha Perera, Julian De Hoog, Kasun Bandara, Saman Halgamuge
Neural Network Attention Based Weather Forecasting Solar Generation Cloud Classification Solar Forecasting

November 15, 2024

A Hard-Label Cryptanalytic Extraction of Non-Fully Connected Deep Neural Networks using Side-Channel Attacks
Benoit Coqueret, Mathieu Carbone, Olivier Sentieys, Gabriel Zaid
Neural Network Deep Neural Network Adversarial Example Network Programming Deep Network Side Channel Hard Label Attack
Adapting the Biological SSVEP Response to Artificial Neural Networks
Emirhan Böge, Yasemin Gunindi, Erchan Aptoula, Nihan Alp, Huseyin Ozkan
Neural Network Artificial Neural Network Neural Response State Visual Evoked Potential Auto Tagging Neuron Importance
Adaptive Physics-Guided Neural Network
David Shulman, Itai Dattner
Neural Network Adaptive Importance ResNet Based Thermal Image Dataset Physic Prediction
Physics-informed neural networks need a physicist to be accurate: the case of mass and heat transport in Fischer-Tropsch catalyst particles
Tymofii Nikolaienko, Harshil Patel, Aniruddha Panda, Subodh Madhav Joshi, Stanislav Jaso, Kaushic Kalyanaraman
Neural Network Physic Informed Neural Network Scientific Research Reaction Diffusion Finite Difference Heat Transfer Tandem Mass
Dense ReLU Neural Networks for Temporal-spatial Model
Zhi Zhang, Carlos Misael Madrid Padilla, Xiaokai Luo, Daren Wang, Oscar Hernan Madrid Padilla
Neural Network Spatio Temporal Rectified Linear Unit Dense Neural Network Intrinsic Dimensionality

November 14, 2024

Learning Parameter Sharing with Tensor Decompositions and Sparsity
Cem Üyük, Mike Lasby, Mohamed Yassin, Utku Evci, Yani Ioannou
Neural Network Vision Transformer Sparsity Increase Tensor Decomposition Parameter Sharing
Physics-informed neural networks (PINNs) for numerical model error approximation and superresolution
Bozhou Zhuang, Sashank Rana, Brandon Jones, Danny Smyl
Neural Network Super Resolution Physic Informed Neural Network Average Approximation Parameter Identification Model Error Numerical Approximation
Improving hp-Variational Physics-Informed Neural Networks for Steady-State Convection-Dominated Problems
Thivin Anandh, Divij Ghose, Himanshu Jain, Pratham Sunkad, Sashikumaar Ganesan, Volker John
Neural Network Physic Informed Neural Network Numerical Method Boundary Condition Self Stabilization Effect Advection Diffusion Reaction
Hybrid deep additive neural networks
Gyu Min Kim, Jeong Min Jeon
Neural Network Multi Layer Efficient Hybrid Hybrid Neural Network Neural Additive Model Traditional Neural Network
Heuristical Comparison of Vision Transformers Against Convolutional Neural Networks for Semantic Segmentation on Remote Sensing Imagery
Ashim Dahal, Saydul Akbar Murad, Nick Rahimi
Neural Network Vision Transformer Semantic Segmentation Deep Convolutional Neural Network Remote Sensing Image State of the Art Segmentation

November 13, 2024

New advances in universal approximation with neural networks of minimal width
Dennis Rochau, Hanno Gottschalk, Robin Chan
Neural Network Universal Approximation Intrinsic Dimension Universal Approximators Minimum Width New Finding
Neural Conjugate Flows: Physics-informed architectures with flow structure
Arthur Bizzi, Lucas Nissenbaum, João M. Pereira
Neural Network Inner Structure Latent Dynamic Architecture Perspective Flow Mood Universal Approximators

November 12, 2024

Emergent field theories from neural networks
Vitaly Vanchurin
Neural Network Field Theory Hamiltonian System Strong Duality
Exploring the loss landscape of regularized neural networks via convex duality
Sungyoon Kim, Aaron Mishkin, Mert Pilanci
Neural Network Loss Landscape Two Layer Neural Network Vector Valued Strong Duality Three Layer Neural Network

Neural Network

Papers

BALI: Learning Neural Networks via Bayesian Layerwise Inference

A Neural Network Training Method Based on Distributed PID Control

Don't Be So Positive: Negative Step Sizes in Second-Order Methods

Making Sigmoid-MSE Great Again: Output Reset Challenges Softmax Cross-Entropy in Neural Network Classification

Variational Bayesian Bow tie Neural Networks with Shrinkage

Distributed solar generation forecasting using attention-based deep neural networks for cloud movement prediction

A Hard-Label Cryptanalytic Extraction of Non-Fully Connected Deep Neural Networks using Side-Channel Attacks

Adapting the Biological SSVEP Response to Artificial Neural Networks

Adaptive Physics-Guided Neural Network

Physics-informed neural networks need a physicist to be accurate: the case of mass and heat transport in Fischer-Tropsch catalyst particles

Dense ReLU Neural Networks for Temporal-spatial Model

Learning Parameter Sharing with Tensor Decompositions and Sparsity

Physics-informed neural networks (PINNs) for numerical model error approximation and superresolution

Improving hp-Variational Physics-Informed Neural Networks for Steady-State Convection-Dominated Problems

Hybrid deep additive neural networks

Heuristical Comparison of Vision Transformers Against Convolutional Neural Networks for Semantic Segmentation on Remote Sensing Imagery

New advances in universal approximation with neural networks of minimal width

Neural Conjugate Flows: Physics-informed architectures with flow structure

Emergent field theories from neural networks

Exploring the loss landscape of regularized neural networks via convex duality