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

July 4, 2024

Psychology of Artificial Intelligence: Epistemological Markers of the Cognitive Analysis of Neural Networks
Michael Pichat
Neural Network Artificial Intelligence Cognitive Process Psychological Phenomenon Post Hoc Epistemic State Artificial Brain
Implicit Hypersurface Approximation Capacity in Deep ReLU Networks
Jonatan Vallin, Karl Larsson, Mats G. Larson
Neural Network ReLU Layer ReLU Activation Deep ReLU Network Approximation Theory Layer ReLU Network Approximation Power
Bias of Stochastic Gradient Descent or the Architecture: Disentangling the Effects of Overparameterization of Neural Networks
Amit Peleg, Matthias Hein
Neural Network Strong Generalization Stochastic Gradient Descent Mixed Effect Absolute Stance Bias Overparametrization Bound
Configurable DOA Estimation using Incremental Learning
Yang Xiao, Rohan Kumar Das
Neural Network Incremental Learning Microphone Array Acoustic Environment Direction of Arrival Estimation

July 3, 2024

Self-supervised Pretraining for Partial Differential Equations
Varun Madhavan, Amal S Sebastian, Bharath Ramsundar, Venkatasubramanian Viswanathan
Neural Network Partial Differential Equation Fourier Neural Operator Self Supervised Pretraining Neural PDE Solver
Terrain Classification Enhanced with Uncertainty for Space Exploration Robots from Proprioceptive Data
Mariela De Lucas Álvarez, Jichen Guo, Raul Domínguez, Matias Valdenegro-Toro
Neural Network Uncertainty Quantification Bayesian Optimization High Uncertainty Anticipation Proprioceptive Sensing Terrain Classification
Solving the inverse problem of microscopy deconvolution with a residual Beylkin-Coifman-Rokhlin neural network
Rui Li, Mikhail Kudryashev, Artur Yakimovich
Neural Network Inverse Problem Microscopy Image Image Deconvolution Residual Model
ShiftAddAug: Augment Multiplication-Free Tiny Neural Network with Hybrid Computation
Yipin Guo, Zihao Li, Yilin Lang, Qinyuan Ren
Neural Network Conventional Neural Network Multiplicative Neural Network
Convergence of Implicit Gradient Descent for Training Two-Layer Physics-Informed Neural Networks
Xianliang Xu, Ting Du, Wang Kong, Ye Li, Zhongyi Huang
Neural Network Physic Informed Neural Network Early Stage Convergence Two Layer Neural Network Gradient Sharing Smooth Activation Function

July 2, 2024

RISC-V R-Extension: Advancing Efficiency with Rented-Pipeline for Edge DNN Processing
Won Hyeok Kim, Hyeong Jin Kim, Tae Hee Han
Neural Network High Efficiency Pipeline System Risc V Hardware Architecture
Robust ADAS: Enhancing Robustness of Machine Learning-based Advanced Driver Assistance Systems for Adverse Weather
Muhammad Zaeem Shahzad, Muhammad Abdullah Hanif, Muhammad Shafique
Neural Network Native Robustness Adverse Weather Driver Assistance System Weather Image Autonomous Perception
Tiny-PULP-Dronets: Squeezing Neural Networks for Faster and Lighter Inference on Multi-Tasking Autonomous Nano-Drones
Lorenzo Lamberti, Vlad Niculescu, Michał Barcis, Lorenzo Bellone, Enrico Natalizio, Luca Benini, Daniele Palossi
Neural Network Autonomous Navigation Genre Classification Nano Drone

July 1, 2024

Fast Iterative Solver For Neural Network Method: II. 1D Diffusion-Reaction Problems And Data Fitting
Zhiqiang Cai, Anastassia Doktorova, Robert D. Falgout, César Herrera
Neural Network Hessian Matrix Newton Method Gauss Newton Reaction Diffusion Iterative Solver Data Fitting dBN Model
DIR-BHRNet: A Lightweight Network for Real-time Vision-based Multi-person Pose Estimation on Smartphones
Gongjin Lan, Yu Wu, Qi Hao
Neural Network Real Time Residual Network Convolutional Block lightWeight Network Smartphone Device Multi Person Pose Estimation
Neural Networks Trained by Weight Permutation are Universal Approximators
Yongqiang Cai, Gaohang Chen, Zhonghua Qiao
Neural Network Universal Approximation Universal Approximators Weight Distribution Permutation Training Training Network
Swish-T : Enhancing Swish Activation with Tanh Bias for Improved Neural Network Performance
Youngmin Seo, Jinha Kim, Unsang Park
Neural Network Bias Related Issue Non Monotonic Activation Function Swish Activation
How Does Overparameterization Affect Features?
Ahmet Cagri Duzgun, Samy Jelassi, Yuanzhi Li
Neural Network Overparametrization Bound Parameterized Model
Expressivity of Neural Networks with Random Weights and Learned Biases
Ezekiel Williams, Avery Hee-Woon Ryoo, Thomas Jiralerspong, Alexandre Payeur, Matthew G. Perich, Luca Mazzucato, Guillaume Lajoie
Neural Network Universal Approximation Behavior Expressivity Style Synaptic Weight Random Weight

June 30, 2024

ModelVerification.jl: a Comprehensive Toolbox for Formally Verifying Deep Neural Networks
Tianhao Wei, Luca Marzari, Kai S. Yun, Hanjiang Hu, Peizhi Niu, Xusheng Luo, Changliu Liu
Neural Network Deep Neural Network Verification Task Flexible Toolkit Verification Strategy
DADEE: Well-calibrated uncertainty quantification in neural networks for barriers-based robot safety
Masoud Ataei, Vikas Dhiman
Neural Network Uncertainty Quantification Uncertainty Estimation Control Barrier Function Robot Safety Calibrated Uncertainty

Neural Network

Papers

Psychology of Artificial Intelligence: Epistemological Markers of the Cognitive Analysis of Neural Networks

Implicit Hypersurface Approximation Capacity in Deep ReLU Networks

Bias of Stochastic Gradient Descent or the Architecture: Disentangling the Effects of Overparameterization of Neural Networks

Configurable DOA Estimation using Incremental Learning

Self-supervised Pretraining for Partial Differential Equations

Terrain Classification Enhanced with Uncertainty for Space Exploration Robots from Proprioceptive Data

Solving the inverse problem of microscopy deconvolution with a residual Beylkin-Coifman-Rokhlin neural network

ShiftAddAug: Augment Multiplication-Free Tiny Neural Network with Hybrid Computation

Convergence of Implicit Gradient Descent for Training Two-Layer Physics-Informed Neural Networks

RISC-V R-Extension: Advancing Efficiency with Rented-Pipeline for Edge DNN Processing

Robust ADAS: Enhancing Robustness of Machine Learning-based Advanced Driver Assistance Systems for Adverse Weather

Tiny-PULP-Dronets: Squeezing Neural Networks for Faster and Lighter Inference on Multi-Tasking Autonomous Nano-Drones

Fast Iterative Solver For Neural Network Method: II. 1D Diffusion-Reaction Problems And Data Fitting

DIR-BHRNet: A Lightweight Network for Real-time Vision-based Multi-person Pose Estimation on Smartphones

Neural Networks Trained by Weight Permutation are Universal Approximators

Swish-T : Enhancing Swish Activation with Tanh Bias for Improved Neural Network Performance

How Does Overparameterization Affect Features?

Expressivity of Neural Networks with Random Weights and Learned Biases

ModelVerification.jl: a Comprehensive Toolbox for Formally Verifying Deep Neural Networks

DADEE: Well-calibrated uncertainty quantification in neural networks for barriers-based robot safety