Results 111 to 120 of about 11,006,319 (257)

Exploring internal representations of self-supervised networks: few-shot learning abilities and comparison with human semantics and recognition of objects

Frontiers in Computational Neuroscience
Recent advances in self-supervised learning have attracted significant attention from both machine learning and neuroscience. This is primarily because self-supervised methods do not require annotated supervisory information, making them applicable to ...
Asaki Kataoka, Yoshihiro Nagano, Masafumi Oizumi   +2 more
doaj   +1 more source

Moisture‐Adaptive Triboelectric Materials and Platforms: Design Strategies, Performance Enhancement, and Applications in Energy Harvesting and Wearable Electronics

Advanced Materials Technologies, EarlyView.
This review summarizes moisture‐adaptive strategies that enable triboelectric nanogenerators (TENGs) to operate across diverse moisture conditions. It examines moisture‐management methods, including exclusion, directional transport, removal, and utilization, with charge‐regulation approaches based on interfacial, dielectric, and structural engineering.
Junzhe Gan, Zhao Sha, Xuehua Zhang, Hoang‐Phuong Phan, Jin Zhang   +4 more
wiley   +1 more source

Customizable Piezo‐Transmittance‐Based Multiaxial Force Sensor With Deep‐Learning‐Assisted Sensing

Advanced Materials Technologies, EarlyView.
Development of a soft tri‐axis piezo‐transmittance sensor with integrated LEDs and photodiodes enables multidirectional force sensing through deformation‐induced optical modulation. A tailored 1D convolutional neural network provides real‐time force direction and intensity prediction, achieving 99.6% classification accuracy and a mean squared error of ...
Filippo Peruzzi, Osman Gul, Wonhee Lee, Seokjoo Cho, Yong‐Jin Yoon, Paola Saccomandi, Inkyu Park   +6 more
wiley   +1 more source

A Weakly Supervised and Self-Supervised Learning Approach for Semantic Segmentation of Land Cover in Satellite Images with National Forest Inventory Data

Remote Sensing
National Forest Inventories (NFIs) provide valuable land cover (LC) information but often lack spatial continuity and an adequate update frequency. Satellite-based remote sensing offers a viable alternative, employing machine learning to extract thematic
Daniel Moraes, Manuel L. Campagnolo, Mário Caetano   +2 more
doaj   +1 more source

Soft Robotic Excretory Care Simulator for Nursing Education: Functional and Perceptual Biomimetics Approach

Advanced Robotics Research, EarlyView.
A soft robotic simulator is developed to replicate the digital removal of feces (DRF), a sensitive yet essential nursing procedure. Integrating soft actuators, sensors, and a realistic rectal model, the simulator balances functional fidelity with perceptual realism. Engineering evaluations and nurse feedback confirm its potential to enhance training in
Shoko Miyagawa, Sota Suzuki, Shizuka Watanabe, Zebing Mao, Young Ah Seong, Toshinori Fujie, Tatsuhiro Horii, Kenjiro Tadakuma, Koichi Suzumori, Hiroyuki Nabae, Shingo Maeda   +10 more
wiley   +1 more source

Blockwise Self-Supervised Learning at Scale

Publisher Copyright: © 2024, Transactions on Machine Learning Research. All rights reserved.Current state-of-the-art deep networks are all powered by backpropagation.
Lecun, Yann, Deny, Stéphane, Siddiqui, Shoaib Ahmed, Krueger, David   +3 more
core   +1 more source

The Future of Research in Cognitive Robotics: Foundation Models or Developmental Cognitive Models?

Advanced Robotics Research, EarlyView.
Research in cognitive robotics founded on principles of developmental psychology and enactive cognitive science would yield what we seek in autonomous robots: the ability to perceive its environment, learn from experience, anticipate the outcome of events, act to pursue goals, and adapt to changing circumstances without resorting to training with ...
David Vernon
wiley   +1 more source

Improving the Robustness of Visual Teach‐and‐Repeat Navigation Using Drift Error Correction and Event‐Based Vision for Low‐Light Environments

Advanced Robotics Research, EarlyView.
Visual teach‐and‐repeat (VTR) navigation allows robots to learn and follow routes without building a full metric map. We show that navigation accuracy for VTR can be improved by integrating a topological map with error‐drift correction based on stereo vision.
Fuhai Ling, Ze Huang, Tony J. Prescott
wiley   +1 more source

Continual Learning for Multimodal Data Fusion of a Soft Gripper

Advanced Robotics Research, EarlyView.
Models trained on a single data modality often struggle to generalize when exposed to a different modality. This work introduces a continual learning algorithm capable of incrementally learning different data modalities by leveraging both class‐incremental and domain‐incremental learning scenarios in an artificial environment where labeled data is ...
Nilay Kushawaha, Egidio Falotico
wiley   +1 more source

Self-Adaptive Training: Bridging Supervised and Self-Supervised Learning

, 2022
We propose self-adaptive training -- a unified training algorithm that dynamically calibrates and enhances training processes by model predictions without incurring an extra computational cost -- to advance both supervised and self-supervised learning of
Zhang, Chao, Zhang, Hongyang, Huang, Lang   +2 more
core