Neural Network Framework

Neural network frameworks are being actively developed to improve the efficiency and capabilities of deep learning models across diverse applications. Current research focuses on enhancing training speed through techniques like sparse backpropagation and novel architectures such as low-rank neural representations and recurrent networks, while also exploring alternatives to traditional backpropagation algorithms. These advancements are impacting various fields, from solving complex scientific problems like inverse medium problems and pricing financial derivatives to improving image captioning and EEG signal classification. The ultimate goal is to create more efficient, robust, and adaptable neural network models for a wider range of tasks.

Papers

October 24, 2024

Cross Spline Net and a Unified World
Linwei Hu, Ye Jin Choi, Vijayan N. Nair
Unified Data Neural Network Framework Non Neural Spline Based

October 5, 2024

FastLRNR and Sparse Physics Informed Backpropagation
Woojin Cho, Kookjin Lee, Noseong Park, Donsub Rim, Gerrit Welper
Back Propagation LOw Rank Low Rank Structure Neural Network Framework Fast FedUL

September 14, 2024

Neumann Series-based Neural Operator for Solving Inverse Medium Problem
Ziyang Liu, Fukai Chen, Junqing Chen, Lingyun Qiu, Zuoqiang Shi
Neural Operator Ill Posed Inverse Problem Neural Network Framework Neumann to Dirichlet Operator

November 16, 2023

Zenkai -- Framework For Exploring Beyond Backpropagation
Greg Short
Deep Learning Deep Neural Network New Framework Back Propagation Deep Learning Network Neural Network Framework

March 21, 2023

Indeterminate Probability Neural Network
Tao Yang, Chuang Liu, Xiaofeng Ma, Weijia Lu, Ning Wu, Bingyang Li, Zhifei Yang, Peng Liu, Lin Sun, Xiaodong Zhang, Can Zhang
Probabilistic Model Probabilistic Neural Network Neural Network Framework

January 19, 2023

Efficient Pricing and Hedging of High Dimensional American Options Using Recurrent Networks
Andrew Na, Justin Wan
Recurrent Neural Network Recurrent Network Deep Recurrent Neural Network Hedging Strategy Neural Network Framework

December 19, 2022

An Extension of Fisher's Criterion: Theoretical Results with a Neural Network Realization
Ibrahim Alsolami, Tomoki Fukai
Feature Selection Theoretical Analysis Extension Study Classification Problem Class Conditional Fisher Weighted Front Door Criterion Neural Network Framework

November 14, 2022

Physics-Guided, Physics-Informed, and Physics-Encoded Neural Networks in Scientific Computing
Salah A Faroughi, Nikhil Pawar, Celio Fernandes, Maziar Raissi, Subasish Das, Nima K. Kalantari, Seyed Kourosh Mahjour
Neural Network Physic Informed Neural Network Scientific Computing Multi Physic Neural Network Framework

July 28, 2022

A Hybrid Complex-valued Neural Network Framework with Applications to Electroencephalogram (EEG)
Hang Du, Rebecca Pillai Riddell, Xiaogang Wang
Convolutional Neural Network Financial Application Efficient Hybrid EEG Signal EEG Classification Complex Valued Convolutional Neural Network Neural Network Framework

June 28, 2022

Secure Forward Aggregation for Vertical Federated Neural Networks
Shuowei Cai, Di Chai, Liu Yang, Junxue Zhang, Yilun Jin, Leye Wang, Kun Guo, Kai Chen
Neural Network Deep Model Vertical Federated Learning Secure Aggregation Neural Network Framework

March 11, 2022

Neural Forecasting of the Italian Sovereign Bond Market with Economic News
Sergio Consoli, Luca Tiozzo Pezzoli, Elisa Tosetti
Neural Forecasting Neural Network Framework Economic Activity

March 3, 2022

A Deep Neural Framework for Image Caption Generation Using GRU-Based Attention Mechanism
Rashid Khan, M Shujah Islam, Khadija Kanwal, Mansoor Iqbal, Md. Imran Hossain, Zhongfu Ye
Recurrent Neural Network Image Captioning Pre Trained Convolutional Neural Network Attention Model Neural Network Framework Image Caption Generation