AZoOptics

Researchers Design AI-Driven Photonic Crystal Fiber Modulator

A deep reinforcement learning framework optimizes silicon-based photonic crystal fiber modulators, achieving ultra-low ...
The New York Times

Jannik Sinner’s upset loss in French Open makes history in 2 ways

Jannik Sinner's loss to Juan Manuel Cerundolo was one of the biggest upsets in recent tennis history. Matthew Stockman / Getty Images When the French Open began, Jannik Sinner was one of the biggest ...
Phys.org

Loss functions and constraints improve sea surface height prediction

In order to understand currents, tides and other ocean dynamics, scientists need to accurately capture sea surface height, or a snapshot of the ocean's surface, including peaks and valleys due to ...
Scientific Research Publishing

Vanishing Gradients in an Artificial Deep Neural Network: The Impact of Activation Functions and Optimization Techniques ()

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 the ...
IEEE

A Hybrid Minkowski-Log-Cosh Loss Function for Robust LSTM-Based Time Series Forecasting

Designing robust loss functions is essential for improving deep learning performance on noisy and sparse time series. We propose the Minkowski–Log–Cosh (MLC) loss, a hybrid formulation that integrates ...
IEEE

Unveiling the Role of Weighted Loss Functions in Deep Learning-Based Nowcasting of Extreme Rainfall Events

Abstract: Nowcasting plays a crucial role in responding to disasters such as flash floods by predicting rainfall in real time. However, existing nowcasting models struggle to accurately predict ...
Medical Xpress

Gene therapy may slow loss of motor function in ALS

Researchers have developed a gene therapy that significantly slowed motor function loss in preclinical models of amyotrophic lateral sclerosis (ALS), offering new hope for treating the devastating ...