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

December 11, 2024

Bayesian optimized deep ensemble for uncertainty quantification of deep neural networks: a system safety case study on sodium fast reactor thermal stratification modeling
Zaid Abulawi, Rui Hu, Prasanna Balaprakash, Yang Liu
Neural Network Uncertainty Quantification Bayesian Optimization Deep Ensemble Bayesian Perspective Aleatoric Uncertainty
Multi-perspective Alignment for Increasing Naturalness in Neural Machine Translation
Huiyuan Lai, Esther Ploeger, Rik van Noord, Antonio Toral
Neural Network Neural Machine Translation View Translation Linguistic Diversity Visual Naturalness Translation Accuracy
Evaluating Different Fault Injection Abstractions on the Assessment of DNN SW Hardening Strategies
Giuseppe Esposito, Juan David Guerrero-Balaguera, Josie Esteban Rodriguez Condia, Matteo Sonza Reorda
Neural Network Direct Assessment Fault Injection Security Hardening
Edge-Splitting MLP: Node Classification on Homophilic and Heterophilic Graphs without Message Passing
Matthias Kohn, Marcel Hoffmann, Ansgar Scherp
Neural Network Graph Drawing Node Classification Message Passing Heterophilic Graph Message Passing Neural Network Single Scene Specific MLP
Towards Precision in Bolted Joint Design: A Preliminary Machine Learning-Based Parameter Prediction
Ines Boujnah, Nehal Afifi, Andreas Wettstein, Sven Matthiesen
Neural Network New Machine Multidimensional Local Precision Rate Model Prediction Non Linear Friction Coefficient
Neural Observation Field Guided Hybrid Optimization of Camera Placement
Yihan Cao, Jiazhao Zhang, Zhinan Yu, Kai Xu
Neural Network Multi Camera Unconstrained Optimization Camera Placement
GLL: A Differentiable Graph Learning Layer for Neural Networks
Jason Brown, Bohan Chen, Harris Hardiman-Mostow, Jeff Calder, Andrea L. Bertozzi
Neural Network Back Propagation Softmax Function Label Propagation Neural Laplace

December 10, 2024

FlashRNN: Optimizing Traditional RNNs on Modern Hardware
Korbinian Pöppel, Maximilian Beck, Sepp Hochreiter
Neural Network Sequence Modeling Traditional RNNs Hardware Design
Fast Track to Winning Tickets: Repowering One-Shot Pruning for Graph Neural Networks
Yanwei Yue, Guibin Zhang, Haoran Yang, Dawei Cheng
Neural Network Graph Neural Network Graph Drawing Edge Pruning Large Scale Graph Graph Learning Task Lottery Ticket Hypothesis Robust Ticket Graph Sparsity

December 8, 2024

Adversarial Transferability in Deep Denoising Models: Theoretical Insights and Robustness Enhancement via Out-of-Distribution Typical Set Sampling
Jie Ning, Jiebao Sun, Shengzhu Shi, Zhichang Guo, Yao Li, Hongwei Li, Boying Wu
Neural Network Open Sampling Adversarial Sample Adversarial DEfense Denoising Model Adversarial Transferability Denoising Performance Robustness Enhancement
Accurate Multi-Category Student Performance Forecasting at Early Stages of Online Education Using Neural Networks
Naveed Ur Rehman Junejo, Muhammad Wasim Nawaz, Qingsheng Huang, Xiaoqing Dong, Chang Wang, Gengzhong Zheng
Neural Network Predictive Performance Prediction Accuracy Student Performance Prediction Student Performance Learning Analytics Online Training Early Stage
Depression detection from Social Media Bangla Text Using Recurrent Neural Networks
Sultan Ahmed, Salman Rakin, Mohammad Washeef Ibn Waliur, Nuzhat Binte Islam, Billal Hossain, Md. Mostofa Akbar
Neural Network Sentiment Analysis Social Medium Underlying Emotion User Sentiment Depression Detection Bangla Text Recurrent Event

December 6, 2024

Stably unactivated neurons in ReLU neural networks
Natalie Brownlowe, Christopher R. Cornwell, Ethan Montes, Gabriel Quijano, Na Zhang
Neural Network ReLU Network Hidden Layer Dead Neuron Training Data Influence
Generating Rectifiable Measures through Neural Networks
Erwin Riegler, Alex Bühler, Yang Pan, Helmut Bölcskei
Neural Network Measure Theoretic Support Set

Neural Network

Papers

Bayesian optimized deep ensemble for uncertainty quantification of deep neural networks: a system safety case study on sodium fast reactor thermal stratification modeling

Multi-perspective Alignment for Increasing Naturalness in Neural Machine Translation

Evaluating Different Fault Injection Abstractions on the Assessment of DNN SW Hardening Strategies

Edge-Splitting MLP: Node Classification on Homophilic and Heterophilic Graphs without Message Passing

Towards Precision in Bolted Joint Design: A Preliminary Machine Learning-Based Parameter Prediction

Neural Observation Field Guided Hybrid Optimization of Camera Placement

GLL: A Differentiable Graph Learning Layer for Neural Networks

FlashRNN: Optimizing Traditional RNNs on Modern Hardware

Fast Track to Winning Tickets: Repowering One-Shot Pruning for Graph Neural Networks

Understanding Gradient Descent through the Training Jacobian

On How Iterative Magnitude Pruning Discovers Local Receptive Fields in Fully Connected Neural Networks

Generative Densification: Learning to Densify Gaussians for High-Fidelity Generalizable 3D Reconstruction

Adversarial Transferability in Deep Denoising Models: Theoretical Insights and Robustness Enhancement via Out-of-Distribution Typical Set Sampling

Accurate Multi-Category Student Performance Forecasting at Early Stages of Online Education Using Neural Networks

Depression detection from Social Media Bangla Text Using Recurrent Neural Networks

Partition of Unity Physics-Informed Neural Networks (POU-PINNs): An Unsupervised Framework for Physics-Informed Domain Decomposition and Mixtures of Experts

Training neural networks without backpropagation using particles

Neighborhood Commonality-aware Evolution Network for Continuous Generalized Category Discovery

Stably unactivated neurons in ReLU neural networks

Generating Rectifiable Measures through Neural Networks