Traditional Neural Network

Traditional neural networks (NNs) aim to model complex relationships within data by adjusting connection weights between nodes, enabling tasks like classification and regression. Current research focuses on addressing limitations such as frequency bias in learning, limited capacity for long sequences, and the "black box" nature of many models, leading to explorations of novel architectures like Kolmogorov-Arnold Networks, biologically-inspired designs (e.g., cortico-basal ganglia-thalamic models), and methods incorporating symbolic reasoning or grey system theory for improved interpretability and efficiency. These advancements enhance NN performance, particularly in areas with limited data or specific computational constraints, impacting diverse fields from scientific machine learning to natural language processing.

Papers

November 14, 2024

Hybrid deep additive neural networks
Gyu Min Kim, Jeong Min Jeon
Neural Network Multi Layer Efficient Hybrid Hybrid Neural Network Neural Additive Model Traditional Neural Network

October 3, 2024

Generalization emerges from local optimization in a self-organized learning network
S. Barland, L. Gil
Strong Generalization Network Programming Graph Structure Local Optimization Traditional Neural Network Network Learning

September 13, 2024

TabKANet: Tabular Data Modeling with Kolmogorov-Arnold Network and Transformer
Weihao Gao, Zheng Gong, Zhuo Deng, Fuju Rong, Chucheng Chen, Lan Ma
Transformer Based Kolmogorov Arnold Network Numerical Data Tabular Model Categorical Feature Traditional Neural Network

May 23, 2024

Understanding the dynamics of the frequency bias in neural networks
Juan Molina, Mircea Petrache, Francisco Sahli Costabal, Matías Courdurier
Neural Network Neural Tangent Kernel Two Layer Neural Network Traditional Neural Network Frequency Bias

March 24, 2024

CBGT-Net: A Neuromimetic Architecture for Robust Classification of Streaming Data
Shreya Sharma, Dana Hughes, Katia Sycara
Neural Network Model Image Classification Task LSTM Model Robust Classification Streaming Data Traditional Neural Network

March 22, 2024

Grey-informed neural network for time-series forecasting
Wanli Xie, Ruibin Zhao, Zhenguo Xu, Tingting Liang
Neural Network Neural Network Model Gray Box Traditional Neural Network

January 3, 2024

A Novel Paradigm for Neural Computation: X-Net with Learnable Neurons and Adaptable Structure
Yanjie Li, Weijun Li, Lina Yu, Min Wu, Jinyi Liu, Wenqiang Li, Meilan Hao
Neural Network Activation Function New Paradigm Neural Computation Traditional Neural Network Neuron Attribution Adaptive Structure

December 15, 2023

Reliable Probabilistic Classification with Neural Networks
Harris Papadopoulos
Neural Network Machine Learning Probabilistic Classifier Traditional Neural Network

November 13, 2023

MetaSymNet: A Dynamic Symbolic Regression Network Capable of Evolving into Arbitrary Formulations
Yanjie Li, Weijun Li, Lina Yu, Min Wu, Jinyi Liu, Wenqiang Li, Meilan Hao, Shu Wei, Yusong Deng
Neural Network Symbolic Regression Adaptive Network Traditional Neural Network Interpretable Mathematical Expression Implicit Formulation

August 31, 2023

Artificial to Spiking Neural Networks Conversion for Scientific Machine Learning
Qian Zhang, Chenxi Wu, Adar Kahana, Youngeun Kim, Yuhang Li, George Em Karniadakis, Priyadarshini Panda
Neural Network Physic Informed Neural Network Spiking Neural Network Activation Function Synthetic to Real Scientific Machine Learning Traditional Neural Network Spiking Neural Network Conversion

August 30, 2023

Beyond Traditional Neural Networks: Toward adding Reasoning and Learning Capabilities through Computational Logic Techniques
Andrea Rafanelli
Complex Reasoning Neuro Symbolic Symbolic Reasoning Knowledge Injection Symbolic Knowledge Traditional Neural Network

June 7, 2023

Long Sequence Hopfield Memory
Hamza Tahir Chaudhry, Jacob A. Zavatone-Veth, Dmitry Krotov, Cengiz Pehlevan
Hopfield Network Traditional Neural Network Sequential Memory

June 3, 2023

Transforming to Yoked Neural Networks to Improve ANN Structure
Xinshun Liu, Yizhi Fang, Yichao Jiang
Classical Neural Network Character Transformation Traditional Neural Network SNN Based Neural Network Structure Deep Learning Module

May 26, 2023

Manifold Regularization for Memory-Efficient Training of Deep Neural Networks
Shadi Sartipi, Edgar A. Bernal
Deep Neural Network Generalization Error Memory Efficiency Memory Efficient Training Traditional Neural Network Manifold Regularization Deep Learning Community

April 3, 2023

Self-building Neural Networks
Andrea Ferigo, Giovanni Iacca
Self Supervised Synaptic Feedback Traditional Neural Network

March 23, 2023

Skip Connections in Spiking Neural Networks: An Analysis of Their Effect on Network Training
Hadjer Benmeziane, Amine Ziad Ounnoughene, Imane Hamzaoui, Younes Bouhadjar
Neural Network General Analysis Mixed Effect Spiking Neural Network Traditional Neural Network Gesture Data Training Network

March 20, 2023

MT-SNN: Enhance Spiking Neural Network with Multiple Thresholds
Xiaoting Wang, Yanxiang Zhang
Neural Network Spiking Neural Network Traditional Neural Network Leaky Integrate and Fire Multi Threshold

February 23, 2023

MetaLDC: Meta Learning of Low-Dimensional Computing Classifiers for Fast On-Device Adaption
Yejia Liu, Shijin Duan, Xiaolin Xu, Shaolei Ren
Edge AI Fast Adaptation Device Inference Traditional Neural Network Device Multi Modal Model Adaptation

November 27, 2022

Traditional Classification Neural Networks are Good Generators: They are Competitive with DDPMs and GANs
Guangrun Wang, Philip H. S. Torr
Adversarial Attack Generative Model Image Generation Supervised ImageNet GAN Model Synchronous Generator Traditional Neural Network

September 24, 2022

Joint Speech Activity and Overlap Detection with Multi-Exit Architecture
Ziqing Du, Kai Liu, Xucheng Wan, Huan Zhou
Overlap Detection Voice Activity Detection Traditional Neural Network Speech Application Multi Exit Joint Task Overlapped Speech Detection