Signature neural patterns may help predict recovery from traumatic brain injury

After traumatic brain injury (TBI), some patients may recover completely, while others retain severe disabilities. Accurately ...

Kolmogorov-Arnold networks bridge AI and scientific discovery by increasing interpretability

AI has successfully been applied in many areas of science, advancing technologies like weather prediction and protein folding ...
IEEE

Adaptive Output Feedback Control Using Lyapunov-Based Deep Recurrent Neural Networks (Lb-DRNNs)

Abstract: Unlike traditional feedforward neural networks, recurrent neural networks (RNNs) possess a recurrent connection that allows them to retain past information. This internal memory enables RNNs ...
IEEE

Neural Network Assisted Walsh Matrix-Based Fault Detection Technique for Power Transformer

Abstract: A new fault detection technique for power transformers using Walsh matrix analysis and a feedforward neural network is presented. Initially, Walsh coefficients are computed from the Walsh ...
Scientific Research Publishing

Mostafanejad, M. (2023) Unification of Popular Artificial Neural Network Activation Functions. arXiv:2302.11007.

ABSTRACT: Artificial deep neural networks (ADNNs) have become a cornerstone of modern machine learning, but they are not immune to challenges. One of the most significant problems plaguing ADNNs is ...