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 ...
IEEE

Research on Artificial Intelligence-Assisted Personalized Learning Path Generation Algorithm Based on Deep Learning

Abstract: This study presents deep learning models' design, implementation, and evaluation to generate personalized learning paths in educational environments. Data was collected from diverse sources, ...
IEEE

Depthwise Convolution with Winograd Algorithm for Efficient CNN Acceleration

This work explores an efficient convolutional acceleration framework tailored for edge devices by integrating Depthwise Convolution with the Winograd algorithm. Through RTL-based hardware ...
IEEE

Comparison of Dehazing Algorithms Using Real-World Hazy Images

Abstract: Single image dehazing has been widely studied by using physics-driven, data-driven, and neural augmentation methods. In this paper, their typical candidates are compared by using real-world ...
IEEE

Research on visual image processing based on YOLO algorithm

Abstract: In the post-epidemic era, the manufacturing industry has undergone profound changes, and the importance of industrial machine vision technology has become increasingly prominent. In the face ...
IEEE

Exploring Color Features with Nasnet CNN and Improved Water Cycle Algorithm for Product Emotional Design

Abstract: This research investigates the multidimensional domain of color image optimization design for emotional product color design, in this case, tricolor product color schemes. By introducing ...
IEEE

AUV Path Planning and Object Tracking Algorithm Based on Reinforcement Learning Under Point Cloud Observation

Abstract: Autonomous underwater vehicles (AUV) play an important role in the process of human exploration of the ocean. However, the existing AUV control methods are faced with the problem of ...

What happened when CNN Travel challenged ChatGPT to come up with guides to our cities

People are increasingly turning to AI-powered tools like ChatGPT for travel-planning advice. Here’s what CNN Travel staff in five major global cities discovered while putting it to the test.
IEEE

Research on the Precision Compensation of Light-Quantum Flowmeter With CPO–PSO–CNN Algorithm

Abstract: In the petroleum industry, light-quantum flowmeters can perform multiphase measurement of gas, liquid, and solid phases, which has attracted significant attention. However, their measurement ...
IEEE

Deep Learning Models for Precision Agriculture: Evaluating CNN Architectures for Accurate Plant Disease Detection

Abstract: Early and precise detection of plant diseases is crucial for enhancing crop yield and minimizing agricultural losses. This paper evaluates the performance of deep learning-based ...
IEEE

SpatialCLIP: Learning 3D-aware Image Representations from Spatially Discriminative Language

Abstract: Contrastive Language-Image Pre-training (CLIP) learns robust visual models through language supervision, making it a crucial visual encoding technique for various applications. However, CLIP ...
IEEE

FCTFANet: A Fused CNN-Transformer Feature Aggregator Network for Image Restoration

Abstract: Convolutional neural networks (CNNs) have been foundational in deep learning architectures for image processing, and recently, Transformer networks have emerged, bringing further ...