Tech Xplore

Reinforcement learning accelerates model-free training of optical AI systems

Optical computing has emerged as a powerful approach for high-speed and energy-efficient information processing. Diffractive ...

AJ2 to Demonstrate Proprietary Algorithm–Hardware Integrated Iris Recognition Platform at CES 2026

SEOCHO-GU, SEOUL, SOUTH KOREA, January 1, 2026 /EINPresswire.com/ — AJ2 (CEO Gil Soo Jung) announced that it will demonstrate its proprietary algorithm–hardware integrated iris recognition platform at ...
IEEE

Multi-Robot Cooperative Inspection Planning of Substation Based on Genetic Algorithm and Deep Reinforcement Learning

Abstract: The safe and reliable operation of power systems relies on the intelligent operation and maintenance (O&M) of substations. However, multi-robot collaborative inspection, an essential ...
IEEE

Hierarchical UAV Autonomous Navigation Algorithm based on Event-Triggered Deep Reinforcement Learning

Abstract: In unknown environments, achieving autonomous navigation for unmanned aerial vehicles (UAVs) is a complex task. Ensuring that UAVs reach their destinations safely and efficiently remains a ...
Physics World

Hybrid deep-learning model eases brachytherapy planning

The BCTVNet neural network provides accurate and rapid target volume delineation for cervical cancer brachytherapy ...
Beebom

What is CNN in Deep Learning? The AI Behind Computer Vision

CNN in deep learning is a special type of neural network that can understand images and visual information. It works just like human vision: first it detects edges, lines and then recognizes faces and ...
IEEE

A Novel Transformer-CNN Hybrid Deep Learning Architecture for Robust Broad-Coverage Diagnosis of Eye Diseases on Color Fundus Images

Abstract: We present a novel and robust deep-learning architecture that takes into account the pathological characteristics of eye diseases on color fundus images. The proposed hybrid architecture is ...
IEEE

SPOT: An Active Learning Algorithm for Efficient Deep Neural Network Training

Abstract: Recent advancements in deep neural networks heavily rely on large-scale labeled datasets. However, acquiring annotations for large datasets can be challenging due to annotation constraints.