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 25, 2024

Gaussian Process Kolmogorov-Arnold Networks
Andrew Siyuan Chen
Neural Network Gaussian Process Kolmogorov Arnold Network Robust Model MNIST Digit
Tracking linguistic information in transformer-based sentence embeddings through targeted sparsification
Vivi Nastase, Paola Merlo
Neural Network Transformer Based Model Sentence Embeddings Random Sparsification Linguistic Information Semantic Role
Lifelong Graph Summarization with Neural Networks: 2012, 2022, and a Time Warp
Jonatan Frank, Marcel Hoffmann, Nicolas Lell, David Richerby, Ansgar Scherp
Neural Network Graph Summarization Time Warp Web Graph
HANNA: Hard-constraint Neural Network for Consistent Activity Coefficient Prediction
Thomas Specht, Mayank Nagda, Sophie Fellenz, Stephan Mandt, Hans Hasse, Fabian Jirasek
Neural Network Mixture Component Thermodynamic Integration Activity Coefficient
Network Inversion of Convolutional Neural Nets
Pirzada Suhail, Amit Sethi
Neural Network Inherent Interpretability Deep Convolutional Neural Network Adversarial Sample Network Inversion
Neural Networks for Generating Better Local Optima in Topology Optimization
Leon Herrmann, Ole Sigmund, Viola Muning Li, Christian Vogl, Stefan Kollmannsberger
Neural Network Topology Optimization Local Optimization Discretization Invariant
Investigating learning-independent abstract reasoning in artificial neural networks
Tomer Barak, Yonatan Loewenstein
Neural Network Cognitive Process Abstract Reasoning Visual Reasoning Task
How Lightweight Can A Vision Transformer Be
Jen Hong Tan
Neural Network Vision Transformer Mixture of Expert Lightweight High Convolution Technique
Context-aware knowledge graph framework for traffic speed forecasting using graph neural network
Yatao Zhang, Yi Wang, Song Gao, Martin Raubal
Neural Network Knowledge Graph Graph Drawing Traffic Forecasting Traffic Speed

July 24, 2024

Towards Neural Network based Cognitive Models of Dynamic Decision-Making by Humans
Changyu Chen, Shashank Reddy Chirra, Maria José Ferreira, Cleotilde Gonzalez, Arunesh Sinha, Pradeep Varakantham
Neural Network Real Human Human Decision Cognitive Process Cognitive Model Cognitive Modeling Dynamic Decision
Nerva: a Truly Sparse Implementation of Neural Networks
Wieger Wesselink, Bram Grooten, Qiao Xiao, Cassio de Campos, Mykola Pechenizkiy
Neural Network Pytorch Model Sparse Matrix Sparse Structure High Sparsity Neural Network Library
Gradient-based inference of abstract task representations for generalization in neural networks
Ali Hummos, Felipe del Río, Brabeeba Mien Wang, Julio Hurtado, Cristian B. Calderon, Guangyu Robert Yang
Neural Network Strong Generalization Scientific Inference Task Representation Task Inference Hierarchical Task
Enhanced Feature Learning via Regularisation: Integrating Neural Networks and Kernel Methods
Bertille Follain, Francis Bach
Neural Network Representation Learning Regularization Model Empirical Risk Minimization Kernel Method Kernel Ridge Regression Transition Kernel
Spectrum-Informed Multistage Neural Networks: Multiscale Function Approximators of Machine Precision
Jakin Ng, Yongji Wang, Ching-Yao Lai
Neural Network Multi Stage Multidimensional Local Precision Rate Spectral Bias Multiscale System
AI-based Density Recognition
Simone Müller, Daniel Kolb, Matthias Müller, Dieter Kranzlmüller
Neural Network Robotics Domain AI Driven Density Invariant

July 23, 2024

Sobolev neural network with residual weighting as a surrogate in linear and non-linear mechanics
A. O. M. Kilicsoy, J. Liedmann, M. A. Valdebenito, F. -J. Barthold, M. G. R. Faes
Neural Network Surrogate Model Dynamic Reweighting Solid Mechanic Surrogate Assisted Version Sobolev Training Sobolev Space
Advances in Land Surface Model-based Forecasting: A comparative study of LSTM, Gradient Boosting, and Feedforward Neural Network Models as prognostic state emulators
Marieke Wesselkamp, Matthew Chantry, Ewan Pinnington, Margarita Choulga, Souhail Boussetta, Maria Kalweit, Joschka Boedecker, Carsten F. Dormann, Florian Pappenberger, Gianpaolo Balsamo
Neural Network Long Short Term Memory Gradient Boosting Prognostic Model Atmospheric Model Land Surface

Neural Network

Papers

Finite Neural Networks as Mixtures of Gaussian Processes: From Provable Error Bounds to Prior Selection

Aspects of importance sampling in parameter selection for neural networks using ridgelet transform

Scalable Graph Compressed Convolutions

Gaussian Process Kolmogorov-Arnold Networks

Tracking linguistic information in transformer-based sentence embeddings through targeted sparsification

Lifelong Graph Summarization with Neural Networks: 2012, 2022, and a Time Warp

HANNA: Hard-constraint Neural Network for Consistent Activity Coefficient Prediction

Network Inversion of Convolutional Neural Nets

Neural Networks for Generating Better Local Optima in Topology Optimization

Investigating learning-independent abstract reasoning in artificial neural networks

How Lightweight Can A Vision Transformer Be

Context-aware knowledge graph framework for traffic speed forecasting using graph neural network

Towards Neural Network based Cognitive Models of Dynamic Decision-Making by Humans

Nerva: a Truly Sparse Implementation of Neural Networks

Gradient-based inference of abstract task representations for generalization in neural networks

Enhanced Feature Learning via Regularisation: Integrating Neural Networks and Kernel Methods

Spectrum-Informed Multistage Neural Networks: Multiscale Function Approximators of Machine Precision

AI-based Density Recognition

Sobolev neural network with residual weighting as a surrogate in linear and non-linear mechanics

Advances in Land Surface Model-based Forecasting: A comparative study of LSTM, Gradient Boosting, and Feedforward Neural Network Models as prognostic state emulators