Results 131 to 140 of about 6,527,322 (289)

Incremental machine learning for image classification

reservedLa capacità di apprendimento incrementale (ovvero l’acquisizione progressiva di nuova conoscenza mantenendo quella già assimilata in passato) dei sistemi machine learning è uno dei più recenti e interessanti sviluppi nel campo dell ...
LAGHETTO, STEVEN
core  

Joint Class and Domain Continual Learning for Decentralized Federated Processes

IEEE Access
Continual learning (CL) is attracting attention to learn in dynamic and non-stationary environments, typical of many real applications, such as those related to Internet of things (IoT).
Chiara Lanza, Tinne Tuytelaars, Marco Miozzo, Eduard Angelats, Paolo Dini   +4 more
doaj   +1 more source

Programmable Pneumatic Actuator System for a Bioinspired Artificial Colon

Advanced Materials Technologies, EarlyView.
A modular soft robotic colon simulator driven by programmable pneumatic actuation is developed to mimic physiological and pathological‐like motility patterns of the large intestine. Finite element–guided design and distributed control enable anatomically realistic deformation for peristalsis, segmentation, and mass movements, supporting capsule ...
Andrew Bickerdike, Bo Tian, Xizheng Fang, Zepeng Wang, Yang Liu, Lucy Adams, Shyam Prasad   +6 more
wiley   +1 more source

On‐Chip Photonic Neural Network Architectures

Advanced Optical Materials, EarlyView.
This review presents a comprehensive overview of on‐chip photonic neural network architectures, covering key photonic building blocks, representative network types, and emerging applications. Recent advances, implementation challenges, and future directions are examined, highlighting the potential of integrated photonics to enable ultrafast, energy ...
Seokjin Hong, Berkay Neseli, Seungyeon Cho, Seungsoo Lee, Yeonjun Kim, Seungyoon Choi, Hyo‐Hoon Park, Hamza Kurt   +7 more
wiley   +1 more source

Incremental Object Keypoint Learning

2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Existing progress in object keypoint estimation primarily benefits from the conventional supervised learning paradigm based on numerous data labeled with pre-defined keypoints. However, these well-trained models can hardly detect the undefined new keypoints in test time, which largely hinders their feasibility for diverse downstream tasks.
Mingfu Liang, Jiahuan Zhou, Xu Zou 0002, Ying Wu 0001   +3 more
openaire   +2 more sources

Scalable Task Planning via Large Language Models and Structured World Representations

Advanced Robotics Research, EarlyView.
This work efficiently combines graph‐based world representations with the commonsense knowledge in Large Language Models to enhance planning techniques for the large‐scale environments that modern robots will need to face. Planning methods often struggle with computational intractability when solving task‐level problems in large‐scale environments ...
Rodrigo Pérez‐Dattari, Zhaoting Li, Robert Babuška, Jens Kober, Cosimo Della Santina   +4 more
wiley   +1 more source

Higher Education: Increased and Equitable Access to Quality Learning Opportunities

, 2019
Given that many developing countries seek to increase participation in Higher Education (HE), COL will work with Ministries of Education and HE Institutions to support capacity building including the development and implementation of Open and Distance ...
Commonwealth of Learning
core   +1 more source

Robust incremental relational learning

, 2009
Real-world learning tasks present a range of issues for learning systems. Learning tasks can be complex and the training data noisy. When operating as part of a larger system, there may be limitations on available memory and computational resources. Learners may also be required to provide results from a stream.
openaire   +3 more sources

From Rigid to Soft Robotic Approaches for Neuroendoscopy

Advanced Robotics Research, EarlyView.
Robotic assistance has had minimal impact on deep intraventricular surgeries, where small‐scale, precision, and reduced invasiveness can contribute to improved patient outcomes. Emerging technologies in rigid, soft, and hybrid robotics are reviewed to identify the most promising mechanisms for deep brain navigation in addition to an attempt to identify
Kieran Gilday, Irena Zubak, Andreas Raabe, Josie Hughes   +3 more
wiley   +1 more source

Privacy-Preserving Federated Class-Incremental Learning

IEEE Transactions on Machine Learning in Communications and Networking
Federated Learning (FL) offers a collaborative training framework, aggregating model parameters from decentralized clients. Many existing models, however, assume static, predetermined data classes within FLa frequently unrealistic assumption.
Jue Xiao, Xueming Tang, Songfeng Lu
doaj   +1 more source