Results 101 to 110 of about 5,879,357 (336)

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

An online deep extreme learning machine based on forgetting mechanism

Dianzi Jishu Yingyong, 2018
The development of deep learning promotes the development of deep online learning, and online learning tends to have strong effectiveness. Based on the principle of online extreme learning machine and the principle of autoencoder of deep extreme learning
Liu Buzhong
doaj   +1 more source

Evaluating unsupervised disentangled representation learning for genomic discovery and disease risk prediction [PDF]

, 2023
Taedong Yun
openalex   +1 more source

Modular, Textile‐Based Soft Robotic Grippers for Agricultural Produce Handling

Advanced Robotics Research, EarlyView.
This article introduces textile‐based pneumatic grippers that transform simple textiles into robust bending actuators. Detailed experiments uncover how cut geometry and fabric selection shape performance. Successful handling of fragile agricultural items showcases the potential of textile robotics for safe, scalable automation in food processing and ...
Zeyu Hou, Eran Beeri Bamani, Joao Buzzatto, Bryan Busby, Lucas Ferrari Gerez   +4 more
wiley   +1 more source

Smart REASSURED Sensors via Machine‐Augmented Printable On‐Paper Arrays

Advanced Sensor Research, EarlyView.
This perspective highlights the emerging role of pattern‐recognition, printable on‐paper sensor arrays for intelligent PoC diagnostics. It discusses how paper's inherent limitations can be overcome through surface modification and scalable printing, and how machine‐learning analysis of cross‐reactive arrays enables multiplexed, low‐cost, and REASSURED ...
Naimeh Naseri, Saba Ranjbar
wiley   +1 more source

GBS-Assisted Quantum Unsupervised Machine Learning on a Universal Programmable Integrated Quantum Chip

Research
Quantum machine learning stands poised as a forefront application for near-term quantum devices, addressing scalability challenges posed by classical computers in handling large datasets.
Huihui Zhu, Wei Luo, Rudai Yan, Chao Ren, Jia Guo, Zichao Zhao, Haoran Ma, Tian Chen, Feng Gao, Leong Chuan Kwek, Hong Cai, Yuehai Wang, Jianyi Yang, Ai-Qun Liu   +13 more
doaj   +1 more source

Modifying Glucose Metabolism Reverses Memory Defects of Alzheimer's Disease Model at Late Stages

Advanced Science, EarlyView.
Using spatial transcriptomics, we show that ferul enanthate (SL‐ZF‐01) reverses episodic‐like memory deficits in aged, but not young, Alzheimer’s disease (AD) mice. SL restores glucose metabolism and Glucose Transporter 1/3 expression via an ‘Aging‐AD‐Rescue’ pattern, rescuing deficits seen in aged AD mice.
Fang Liu, Yiyu‐Li Tang, Zong‐Bo Zhang, Ya‐Hong Tan, Si‐Hui Lin, Ni‐Ya Wang, Jin‐Nan Li, Zhi‐Jie Pan, Jian‐Feng Li, Jing‐Fei Huang, Yu‐Qiang Ding, Chun‐Ming Guo, Lin Xu, Cheng Peng, Qi‐Xin Zhou   +14 more
wiley   +1 more source

NDST3‐Induced Epigenetic Reprogramming Reverses Neurodegeneration in Parkinson's Disease

Advanced Science, EarlyView.
NDST3‐mediated epigenetic reprogramming revitalizes neuronal circuits in the substantia nigra and striatum to halt dopaminergic neuron degeneration and restore motor function in Parkinson's disease models. This strategy promotes neuronal maintenance and functional recovery, highlighting NDST3's therapeutic potential in neurodegenerative disorders ...
Yujung Chang, Yongwoo Na, Hyeonjoo Im, Garam Yang, Seungseon Yang, Hyun Soo Shim, Chunggoo Kim, GyeungYun Kim, Hyeok Ju Park, Hee Young Kim, Seung Eun Lee, Wonwoong Lee, Yoon Ha, Sungho Park, Jieun Kim, Won‐Young Cho, Woong Sun, Jong‐Seo Kim, Junsang Yoo   +18 more
wiley   +1 more source

Unsupervised end-to-end training with a self-defined target

Neuromorphic Computing and Engineering
Designing algorithms for versatile AI hardware that can learn on the edge using both labeled and unlabeled data is challenging. Deep end-to-end training methods incorporating phases of self-supervised and supervised learning are accurate and adaptable to
Dongshu Liu, Jérémie Laydevant, Adrien Pontlevy, Damien Querlioz, Julie Grollier   +4 more
doaj   +1 more source

Investigating Contrastive Pair Learning’s Frontiers in Supervised, Semisupervised, and Self-Supervised Learning

Journal of Imaging
In recent years, contrastive learning has been a highly favored method for self-supervised representation learning, which significantly improves the unsupervised training of deep image models. Self-supervised learning is a subset of unsupervised learning
Bihi Sabiri, Amal Khtira, Bouchra El Asri, Maryem Rhanoui   +3 more
doaj   +1 more source