NPE-DRL: Enhancing Perception-Constrained Obstacle Avoidance with Nonexpert Policy-Guided Reinforcement Learning

Engineering, Aerospace Engineering, Information Science, Computer Science, Artificial Intelligence,
UAVs   Obstacle avoidance   Deep reinforcement learning   Nonexpert policy   Perception-constrained   Sample efficiency   Monocular vision  

Research on Improving UAV Obstacle Avoidance in Vision-Constrained Environments Based on Nonexpert Policy Reinforcement Learning In recent years, unmanned aerial vehicles (UAVs) have gained widespread application in civilian fields such as package delivery, risk assessment, and emergency rescue, owing to their superior maneuverability and versatili...

Learning Neural Network Classifiers by Distributing Nearest Neighbors on Adaptive Hypersphere

Learning Neural Network Classifiers by Distributing Nearest Neighbors on Adaptive Hypersphere

Information Science, Computer Science, Artificial Intelligence,
neural network classifiers   adaptive hypersphere   nearest neighbors   contrastive loss   local optima   embedding space scalability  

Adaptive Hypersphere Neural Network Classifier: Overview of ASNN Research Introduction and Research Background In recent years, with the development of artificial intelligence and deep learning, neural networks (NNs) have been widely applied to classification tasks. The essence of these tasks lies in establishing decision boundaries through neural ...

Knowledge Probabilization in Ensemble Distillation: Improving Accuracy and Uncertainty Quantification for Object Detectors

Information Science, Computer Science, Artificial Intelligence,
knowledge probabilization   ensemble distillation   object detection   uncertainty quantification   deep neural networks   accuracy improvement   feature knowledge  

Research on the Application of Knowledge Probabilization in Ensemble Distillation Academic Background: Significance of the Research and Problem Statement In recent years, deep neural networks (DNNs) have found broad applications in safety-critical fields such as autonomous driving, medical diagnosis, and climate prediction due to their outstanding ...

Efficient CORDIC-based Activation Function Implementations for RNN Acceleration on FPGAs

Engineering, Electrical Engineering, Information Science, Electronic Information, Computer Science, Artificial Intelligence,
CORDIC   RNN   activation function   FPGA   hardware acceleration   natural language processing   edge devices  

Efficient Implementation of RNN Activation Functions: Breakthroughs in CORDIC Algorithms and FPGA Hardware Acceleration Background and Research Significance In recent years, with the rapid advancement of deep learning technologies, Recurrent Neural Networks (RNNs), particularly Long Short-Term Memory (LSTM) networks, have demonstrated powerful capa...

Boosting Few-Shot Semantic Segmentation with Prior-Driven Edge Feature Enhancement Network

Boosting Few-Shot Semantic Segmentation with Prior-Driven Edge Feature Enhancement Network

Information Science, Computer Science, Artificial Intelligence,
few-shot learning   semantic segmentation   edge features   prior information   deep learning   object boundaries   edge enhancement  

A New Approach to Enhance Few-Shot Semantic Segmentation: Prior-Driven Edge Feature Enhancement Network In the field of artificial intelligence, semantic segmentation is a core technology in computer vision that aims to assign semantic category labels to every pixel in an image. However, traditional semantic segmentation methods rely on large amoun...

Partial Multi-Label Learning via Label-Specific Feature Corrections

Information Science, Computer Science, Artificial Intelligence,
partial multi-label learning   label-specific features   feature corrections   multi-label learning   machine learning   meta-learning   weak supervision  

Frontier Research in Partial Multi-Label Learning: A New Method Based on Label-Specific Feature Corrections In recent years, partial multi-label learning (PML) has become a hot research topic in the field of machine learning. With the rise of crowdsourcing platforms, the cost of data annotation has dropped significantly, but the quality of annotati...