Results 111 to 120 of about 137,057 (303)

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

Deep Contrastive Learning for High‐Throughput Prediction of Drug Resistance Mutations from Sequences

Advanced Science, EarlyView.
This study presents DeepMutDTA, a deep learning framework aimed at predicting mutation‐induced changes in protein‐drug interactions and prioritizing variants potentially linked to drug resistance. Trained on large‐scale data, it incorporates SimSiam‐MuTF, a label‐aware contrastive fine‐tuning strategy that encourages separation between WT and MT ...
Xiaowen Hu, Pan Zhang, Shangqian Wu, Hao Sun, Minwei Li, Sophia Tsoka, Zizhang Sheng, Lei Deng   +7 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

Dissecting the Ecological Structure of Health and Disease in the Global Gut Microbiome

Advanced Science, EarlyView.
We introduce Wiredancer, a framework that identifies three continuous ecological factors of the gut microbiota. These factors exhibit distinct patterns across health and disease, jointly capturing disrupted ecological stability and offering a new perspective for precision diagnostics and therapeutic strategies.
Baoyuan Zhu, Shuhao Chen, Yunheng Diao, Wei Wang, Yuanyuan Huang, Liqin Liang, Xiaodan Lu, Rui Han, Minxin Guo, Zhaobo Li, Shuhong Wang, Hehua Li, Chenyu Liu, Jing Zhou, Dongsheng Xiong, Xiaobo Li, Yuping Ning, Xuetao Shi, Fengchun Wu, Kai Wu   +19 more
wiley   +1 more source

Minimally-Supervised Morphological Segmentation using Adaptor Grammars [PDF]

, 2013
This paper explores the use of Adaptor Grammars, a nonparametric Bayesian modelling framework, for minimally supervised morphological segmentation. We compare three training methods: unsupervised training, semi-supervised training, and a novel model ...
Sirts, Kairit, Goldwater, Sharon; id_orcid   +1 more
core  

Unsupervised Intralingual and Cross-Lingual Speaker Adaptation for HMM-Based Speech Synthesis Using Two-Pass Decision Tree Construction [PDF]

, 2010
Hidden Markov model (HMM)-based speech synthesis systems possess several advantages over concatenative synthesis systems. One such advantage is the relative ease with which HMM-based systems are adapted to speakers not present in the training dataset ...

core   +2 more sources

Unsupervised spectral learning of FSTs [PDF]

, 2013
Finite-State Transducers (FST) are a standard tool for modeling paired input output sequences and are used in numerous applications, ranging from computational biology to natural language processing. Recently Balle et al.
Carreras Pérez, Xavier, Quattoni, Ariadna Julieta, Bailly, Raphaël   +2 more
core   +2 more sources

An Integrated NLP‐ML Framework for Property Prediction and Design of Steels

Advanced Science, EarlyView.
This study presents a data‐driven framework that uses language‐processing techniques to interpret steel processing descriptions and machine‐learning models to predict mechanical properties. By organising complex process histories into meaningful groups and enabling rapid property forecasts, the work supports faster, more informed steel design through ...
Kiran Devraju, Adithya Umanath Rai, Jose Thomson, Marzie Ghorbani, Shujing Zhao, Nick Birbilis   +5 more
wiley   +1 more source

When Low Rank Representation Based Hyperspectral Imagery Classification Meets Segmented Stacked Denoising Auto-Encoder Based Spatial-Spectral Feature

Remote Sensing, 2018
When confronted with limited labelled samples, most studies adopt an unsupervised feature learning scheme and incorporate the extracted features into a traditional classifier (e.g., support vector machine, SVM) to deal with hyperspectral imagery ...
Cong Wang, Lei Zhang, Wei Wei, Yanning Zhang   +3 more
doaj   +1 more source