Conventional Neural Network

Conventional neural networks (CNNs) are computational models inspired by the structure and function of the brain, primarily used for tasks like image classification and regression. Current research focuses on improving CNN efficiency (e.g., through multiplication-free operators and sparsification techniques), enhancing their robustness (e.g., by addressing vulnerabilities to model inversion attacks and improving prediction interval reliability), and exploring alternative architectures (e.g., graph-based networks and networks with interconnected hidden neurons for faster convergence). These advancements aim to improve accuracy, reduce computational costs, and address critical concerns like data privacy, ultimately impacting various fields from healthcare to physics simulations.

Papers

July 3, 2024

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

February 1, 2024

BrainLeaks: On the Privacy-Preserving Properties of Neuromorphic Architectures against Model Inversion Attacks
Hamed Poursiami, Ihsen Alouani, Maryam Parsa
Privacy Preserving Model Inversion Attack Gradient Based Attack Neural Computation Neuromorphic Architecture Inversion Attack Conventional Neural Network

December 15, 2023

Reliable Prediction Intervals with Regression Neural Networks
Harris Papadopoulos, Haris Haralambous
Conformal Prediction Prediction Interval Point Prediction Regression Network Conventional Neural Network

December 3, 2023

Graph Coordinates and Conventional Neural Networks -- An Alternative for Graph Neural Networks
Zheyi Qin, Randy Paffenroth, Anura P. Jayasumana
Graph Neural Network Graph Based Learning Coordinate Based Coordinate Network Conventional Neural Network Topological Neural Network

August 16, 2023

Membrane Potential Batch Normalization for Spiking Neural Networks
Yufei Guo, Yuhan Zhang, Yuanpei Chen, Weihang Peng, Xiaode Liu, Liwen Zhang, Xuhui Huang, Zhe Ma
Neural Network Convolution Layer Neuromorphic Datasets Nonlinear Activation Conventional Neural Network Based Normalization

May 17, 2023

Connected Hidden Neurons (CHNNet): An Artificial Neural Network for Rapid Convergence
Rafiad Sadat Shahir, Zayed Humayun, Mashrufa Akter Tamim, Shouri Saha, Md. Golam Rabiul Alam
Neural Network Deep Network Biological Neural Network Convergence Performance Hidden Neuron Conventional Neural Network

April 30, 2023

Sparsifying Spiking Networks through Local Rhythms
Wilkie Olin-Ammentorp
Neural Network Spiking Neural Network Computation Method Spike Protein Novel Application R Theta Local Neighborhood Pattern Conventional Neural Network

November 11, 2022

Spectral Evolution and Invariance in Linear-width Neural Networks
Zhichao Wang, Andrew Engel, Anand Sarwate, Ioana Dumitriu, Tony Chiang
Learning Rate Neural Tangent Kernel Spectral Feature Alpha Invariance Conventional Neural Network

June 21, 2022

On the Intrinsic Structures of Spiking Neural Networks
Shao-Qun Zhang, Jia-Yi Chen, Jin-Hui Wu, Gao Zhang, Huan Xiong, Bin Gu, Zhi-Hua Zhou
Spiking Neural Network SNN Model P System Conventional Neural Network Intrinsic Structure

April 9, 2022

Neuronal diversity can improve machine learning for physics and beyond
Anshul Choudhary, Anil Radhakrishnan, John F. Lindner, Sudeshna Sinha, William L. Ditto
Neural Network Machine Learning Theoretical Physic Hamiltonian Neural Network Homogeneous Neural Network Conventional Neural Network Neuronal Diversity