AIMC Topic: Learning

Clear Filters Showing 91 to 100 of 1476 articles

Brain-Inspired Learning, Perception, and Cognition: A Comprehensive Review.

IEEE transactions on neural networks and learning systems
The progress of brain cognition and learning mechanisms has provided new inspiration for the next generation of artificial intelligence (AI) and provided the biological basis for the establishment of new models and methods. Brain science can effectiv...

Curriculum is more influential than haptic feedback when learning object manipulation.

Science advances
Dexterous manipulation remains an aspirational goal for autonomous robotic systems, particularly when learning to lift and rotate objects against gravity with intermittent finger contacts. We use model-free reinforcement learning to compare the effec...

Mastering diverse control tasks through world models.

Nature
Developing a general algorithm that learns to solve tasks across a wide range of applications has been a fundamental challenge in artificial intelligence. Although current reinforcement-learning algorithms can be readily applied to tasks similar to w...

Enhancing target speaker extraction with Hierarchical Speaker Representation Learning.

Neural networks : the official journal of the International Neural Network Society
Target speaker extraction aims to obtain the speech of the specific speaker from a mixture of multiple voices. The conventional approach exploits the target speaker embeddings from a pre-recorded speech segment as auxiliary information, providing pri...

[How older people are learning through artificial intelligence-assisted health technologies : Cute seals and nervous fall sensors].

Zeitschrift fur Gerontologie und Geriatrie
BACKGROUND: With the growing use of artificial intelligence (AI) in various areas of life, AI technologies are increasingly being developed for the nursing and care of older people and are intended to contribute to greater safety for older people in ...

Exploring the categories of students' interest and their relationships with deep learning in technology supported environments.

Scientific reports
Interest is not only the starting point to begin a wonderful learning journey for students, but also an important driver for deep learning and continuous progress. This study used latent profile analysis (LPA), multiple logistic regression analysis, ...

Select for better learning: identifying high-quality training data for a multimodal cyclic transformer.

Journal of neural engineering
. Tonic-clonic seizures (TCSs), which present a significant risk for sudden unexpected death in epilepsy, require accurate detection to enable effective long-term monitoring. Previous studies have demonstrated the advantages of multimodal seizure det...

LNet: Localized and Layered Reparameterization for incremental learning.

Neural networks : the official journal of the International Neural Network Society
Model-based class incremental learning (CIL) methods aim to address the challenge of catastrophic forgetting by retaining certain parameters and expanding the model architecture. However, retaining too many parameters can lead to an overly complex mo...

AI optimization algorithms enhance higher education management and personalized teaching through empirical analysis.

Scientific reports
This research investigates the application of artificial intelligence (AI) optimization algorithms in higher education management and personalized teaching. Through a comprehensive literature review, theoretical analysis, and empirical study, the pot...

Bio-inspired neural networks with central pattern generators for learning multi-skill locomotion.

Scientific reports
Biological neural circuits, central pattern generators (CPGs), located at the spinal cord are the underlying mechanisms that play a crucial role in generating rhythmic locomotion patterns. In this paper, we propose a novel approach that leverages the...