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 21, 2024

On The Global Convergence Of Online RLHF With Neural Parametrization
Mudit Gaur, Amrit Singh Bedi, Raghu Pasupathy, Vaneet Aggarwal
Large Language Model Reinforcement Learning Neural Network Reinforcement Learning From Human Feedback Global Convergence Reward Learning AI Alignment
All You Need is an Improving Column: Enhancing Column Generation for Parallel Machine Scheduling via Transformers
Amira Hijazi, Osman Ozaltin, Reha Uzsoy
Neural Network Transformer Megatron Decepticons Column Generation Machine Scheduling

October 20, 2024

SNAP: Stopping Catastrophic Forgetting in Hebbian Learning with Sigmoidal Neuronal Adaptive Plasticity
Tianyi Xu, Patrick Zheng, Shiyan Liu, Sicheng Lyu, Isabeau Prémont-Schwarz
Neural Network Catastrophic Forgetting Snap Video
Fractional-order spike-timing-dependent gradient descent for multi-layer spiking neural networks
Yi Yang, Richard M. Voyles, Haiyan H. Zhang, Robert A. Nawrocki
Neural Network Spike Timing Dependent Plasticity Fractional Derivative Loss Gradient Fractional Order Gradient

October 19, 2024

October 18, 2024

Parallel Backpropagation for Inverse of a Convolution with Application to Normalizing Flows
Sandeep Nagar, Girish Varma
Neural Network Application Proficiency Normalizing Flow Direct Convolution Convolution Layer Inverse Task
How Does Data Diversity Shape the Weight Landscape of Neural Networks?
Yang Ba, Michelle V. Mancenido, Rong Pan
Neural Network Generative Model Data Augmentation Strong Generalization Regularization Model Data Augmentation Method Data Diversity Weight Re Mapping
Large Language Models Are Overparameterized Text Encoders
Thennal D K, Tim Fischer, Chris Biemann
Large Language Model Neural Network Contrastive Training
How Do Training Methods Influence the Utilization of Vision Models?
Paul Gavrikov, Shashank Agnihotri, Margret Keuper, Janis Keuper
Neural Network Vision Model ImageNet 1k Self Supervised Training Task Complexity Learnable Parameter Resource Utilization Training Method
Advancing Physics Data Analysis through Machine Learning and Physics-Informed Neural Networks
Vasileios Vatellis
Neural Network Machine Learning Physic Informed Neural Network Scientific Research Physic Data
Universal approximation results for neural networks with non-polynomial activation function over non-compact domains
Ariel Neufeld, Philipp Schmocker
Neural Network Activation Function Universal Approximation Polynomial Activation Layer Neural Network

October 17, 2024

Self Supervised Deep Learning for Robot Grasping
Danyal Saqib, Wajahat Hussain
Neural Network Deep Learning Convolutional Neural Network Robot Person Robotic Grasping Self Information Human Labeling
Scaling Wearable Foundation Models
Girish Narayanswamy, Xin Liu, Kumar Ayush, Yuzhe Yang, Xuhai Xu, Shun Liao, Jake Garrison, Shyam Tailor, Jake Sunshine, Yun Liu, Tim Althoff, Shrikanth Narayanan, Pushmeet Kohli, Jiening Zhan, Mark Malhotra, Shwetak Patel, Samy Abdel-Ghaffar, Daniel McDuff
Neural Network Wearable Sensor Scalable Model Sensing Model
Partially Trained Graph Convolutional Networks Resist Oversmoothing
Dimitrios Kelesis, Dimitris Fotakis, Georgios Paliouras
Neural Network Jina Embeddings Deep Network Node Embeddings
PiLocNet: Physics-informed neural network on 3D localization with rotating point spread function
Mingda Lu, Zitian Ao, Chao Wang, Sudhakar Prasad, Raymond H. Chan
Neural Network Localization Focus Point Spread Function 3D Localization Localization Network

October 16, 2024

FusionLLM: A Decentralized LLM Training System on Geo-distributed GPUs with Adaptive Compression
Zhenheng Tang, Xueze Kang, Yiming Yin, Xinglin Pan, Yuxin Wang, Xin He, Qiang Wang, Rongfei Zeng, Kaiyong Zhao, Shaohuai Shi, Amelie Chi Zhou, Bo Li, Bingsheng He, Xiaowen Chu
Neural Network Deep Neural Network DNN Framework Machine Learning Framework LLM Robustness Adaptive Compression Geo Distributed
Towards Arbitrary QUBO Optimization: Analysis of Classical and Quantum-Activated Feedforward Neural Networks
Chia-Tso Lai, Carsten Blank, Peter Schmelcher, Rick Mukherjee
Neural Network General Analysis Quadratic Unconstrained Binary Optimization Performance Box Qubo

Neural Network

Papers

On The Global Convergence Of Online RLHF With Neural Parametrization

All You Need is an Improving Column: Enhancing Column Generation for Parallel Machine Scheduling via Transformers

SNAP: Stopping Catastrophic Forgetting in Hebbian Learning with Sigmoidal Neuronal Adaptive Plasticity

Fractional-order spike-timing-dependent gradient descent for multi-layer spiking neural networks

Less is More: Parameter-Efficient Selection of Intermediate Tasks for Transfer Learning

NeuralMAG: Fast and Generalizable Micromagnetic Simulation with Deep Neural Nets

GL-NeRF: Gauss-Laguerre Quadrature Enables Training-Free NeRF Acceleration

Water quality polluted by total suspended solids classified within an Artificial Neural Network approach

Parallel Backpropagation for Inverse of a Convolution with Application to Normalizing Flows

How Does Data Diversity Shape the Weight Landscape of Neural Networks?

Large Language Models Are Overparameterized Text Encoders

How Do Training Methods Influence the Utilization of Vision Models?

Advancing Physics Data Analysis through Machine Learning and Physics-Informed Neural Networks

Universal approximation results for neural networks with non-polynomial activation function over non-compact domains

Self Supervised Deep Learning for Robot Grasping

Scaling Wearable Foundation Models

Partially Trained Graph Convolutional Networks Resist Oversmoothing

PiLocNet: Physics-informed neural network on 3D localization with rotating point spread function

FusionLLM: A Decentralized LLM Training System on Geo-distributed GPUs with Adaptive Compression

Towards Arbitrary QUBO Optimization: Analysis of Classical and Quantum-Activated Feedforward Neural Networks