Install
Please confirm you are human
This browser or connection looks automated. Press and continuously hold the control for 3 seconds to enable Google-hosted web results and, when separately allowed, AI-assisted answers.
A successful check enables 100 search requests. Interactive access does not authorize scraping, systematic collection, or reuse of search output.
News
Applied Sciences, Vol. 16, Pages 9083: PV-STAM: Velocity-Aware Attention for Mapless Deep Reinforcement Learning Navigation in Dynamic Environments
27+ min ago (678+ words) Mapless deep reinforcement learning (DRL) navigation in dynamic indoor environments is difficult under single-frame 2D LiDAR, which reports where an obstacle is but not whether it is approaching. We introduce the Positional-Velocity Spatio-Temporal Attention Module (PV-STAM), a compact perception block (19,968 trainable…...
New Fuzzy Machine Learning Model Tackles Imbalanced Data With Striking
17+ hour, 9+ min ago (94+ words) Imbalanced data is one of the most stubborn problems in modern machine learning. Whenever a dataset contains far more examples of one class than another, standard classifiers tend to favor the majority class, quietly ignoring the rare but often critical…...
Reinforcement Learning, Part 12: AlphaZero — Where Search, Self-Play, and Confidence Bounds Meet
1+ day, 8+ hour ago (690+ words) Three separate threads from earlier in this series converge in one place. Part 8 asked what happens when an agent explicitly models its…Continue reading on Medium » Reinforcement Learning, Part 12: AlphaZero — Where Search, Self-Play, and Confidence Bounds Meet Three separate threads…...
Kolmogorov-Arnold Networks: Moving the Nonlinearity From the Node to the Edge
1+ day, 8+ hour ago (76+ words) Day 10 of an ongoing daily series on advanced machine learning concepts Abstract The multilayer perceptron has been the …...
Iterative genetic programming builds feature subsets for high-dimensional
1+ day, 10+ hour ago (55+ words) High-dimensional data have become the defining challenge of modern machine learning, and a team of researchers in China has now unveiled a new evolutionary algorithm that promises to make sense of the overwhelming number of variables found in gene expression…...
Multi-task framework fuses infrared and visible images for better semantics
2+ day, 6+ hour ago (98+ words) In a development that could reshape how machines see in the dark, a team of researchers at Jiangxi University of Science and Technology in Nanchang, China, has unveiled a new artificial intelligence framework that fuses infrared and visible-light images while…...
Adaptive Fisher dictionary learning tailored to category-specific
2+ day, 6+ hour ago (55+ words) A team of machine learning researchers in China has unveiled a new supervised dictionary learning model that promises faster image classification in scenarios where training data is scarce, a persistent challenge in fields ranging from medical imaging to face recognition....
Federated learning framework detects time series anomalies while preserving
4+ day, 4+ hour ago (55+ words) Anomaly detection has become one of the most critical technologies of the modern connected world, quietly guarding everything from hospital patients to water treatment plants. Every heartbeat monitored by a wearable device, every vibration sensor on an industrial assembly line,…...
Shape-aware transformer boosts multivariate time series classification
4+ day, 16+ hour ago (86+ words) A new artificial intelligence model that reads time series data the way a skilled human analyst might—by looking at both the overall shape of a signal and the raw numbers behind it—has demonstrated record-setting performance across a broad…...
Cross-domain remote sensing scene classification via Swin Transformer with domain-invariant feature learning
1+ week, 2+ day ago (15+ words) Springer Nature Link...