Results 121 to 130 of about 603,409 (311)

Solution‐Processed Two‐Dimensional Indium Oxide on Sodium‐Embedded Alumina for Reconfigurable Optoelectronic Synaptic Transistors

Advanced Functional Materials, EarlyView.
Wafer‐scale two‐dimensioanl In2Se3 oxidized into InOx on sodium‐embedded beta‐alumina enables multifunctional reconfigurable electronics. Sodium ions accumulate within distinct spatial distribution under drain‐controlle and gate‐controlled operation. Drain‐control operation gives controllability of ultraviolet‐driven optoelectronic synaptic conductance
Jinhong Min, Yonghyun Albert Kwon, Hyunbin Kim, Jihyun Kim, Myeongjin Jung, Jaewon Heo, Gwang Ya Kim, Vlastimil Mazanek, Zdeněk Sofer, In Soo Kim, Jeong Ho Cho, Hyesung Park, Sang Min Won, Joohoon Kang   +13 more
wiley   +1 more source

MGPT: A Multi‐task Graph Prompt Learning Framework for Drug Discovery

Advanced Science
Predicting accurate drug associations, including drug‐target interactions, drug side effects, and drug‐disease relationships, is crucial in biomedical research and precision medicine.
Yang Li, Youhan Sun, Xinyu Qin, Xin Gao, Guohua Wang   +4 more
doaj   +1 more source

Leveraging Multi-task Learning for Unambiguous and Flexible Deep Neural Network Watermarking

, 2022
Deep neural networks are playing an important role in many real-life applications. An important prerequisite in commercializing deep neural networks is the identification of their genuine owners.
Liew, AWC, Yang, L, Li, F, Wang, S
core  

Machine Learning‐Assisted Inverse Design of Soft and Multifunctional Hybrid Liquid Metal Composites

Advanced Functional Materials, EarlyView.
A machine learning framework is presented for inverse design of synthesizable multifunctional composites containing both liquid metal and solid inclusions. By integrating physics‐based modeling, data‐driven prediction, and Bayesian optimization, the approach enables intelligent design of experiments to identify optimal compositions and realize these ...
Lijun Zhou, Yunsik Ohm, Ren‐Mian Chin, Olivia Kerr, Krithika Manohar, Mohammad H. Malakooti   +5 more
wiley   +1 more source

Identifying the task characteristics that predict children's construction task performance [PDF]

, 2010
Construction tasks form a major part of children’s play and can be linked to achievement in maths and science. However there is a lack of understanding of construction task ability and development.
Richardson, Miles, Brown, Stephen L., Miles Richardson, Brown, Steve, Steve Croker, Brown, S, Jones, Gary, Richardson, M, Steve Brown, Croker, S, Croker, Steve, Gary Jones, Jones, G   +12 more
core   +1 more source

Integrated Field‐Free SOT Domain‐Wall Synapses and MTJ Stochastic Neurons for Hardware Boltzmann Machines

Advanced Functional Materials, EarlyView.
Field‐free spin‐orbit torque domain‐wall synapses integrated with stochastic MTJ neurons enable compact hardware Boltzmann machines. Leveraging intrinsic stochasticity and multi‐level conductance, the system achieves efficient probabilistic learning with high accuracy, demonstrating a scalable spintronic platform for energy‐efficient edge AI.
Aijaz H. Lone, Meng Tang, Camelia Florica, Bin He, Jingkai Xu, Selma Amara, Georgian Melinte, Xixiang Zhang, Gianluca Setti   +8 more
wiley   +1 more source

Multimodal Perception and Machine Learning‐Empowered Human Machine Interfaces With Double‐Network Hydrogel Fibers

Advanced Functional Materials, EarlyView.
This work develops polyacrylamide‐alginate (PAM‐Alg) double‐network hydrogel fibers for multimodal perception and intelligent human‐machine interfaces. The covalent‐ionic network provides high strength, toughness, and stable conductivity. Easily woven into wearables and integrated with soft robots, the fibers enable object and temperature recognitions ...
Yujue Yang, Minyu Qiu, Di Tan, Xinlong Liu, Junze Zhang, Ziyu He, Jing Han, Yuanyuan Gao, Zihua Li, Hong Fu, Bingang Xu   +10 more
wiley   +1 more source

Learning Potential Functions and their Representations for Multi-Task Reinforcement Learning [PDF]

, 2014
In multi-task learning, there are roughly two approaches to discovering representations. The first is to discover task relevant representations, i.e., those that compactly represent solutions to particular tasks. The second is to discover domain relevant
Whiteson, S., Snel, M.
core   +1 more source

Ultrasmall High‐Entropy Materials: Nanoscale Effects, Synthesis, and Mechanistic Insights

Advanced Functional Materials, EarlyView.
This review article focuses on sub‐10 nm high‐entropy materials that combine nanoscale design with complex compositions for next‐generation applications. ABSTRACT Ultrasmall high‐entropy nanomaterials (USHENMs, <10 nm) merge multicomponent chemistry with size‐dependent effects, forming a distinct class of materials with unprecedented properties.
Yueyue He, Wenbo Wang, Simon Schweidler, Yanjiao Ma, Ben Breitung, Torsten Brezesinski   +5 more
wiley   +1 more source

Multi-task Sequence to Sequence Learning

, 2015
10 pages, 4 figures, ICLR 2016 camera-ready, added parsing SOTA ...
Minh-Thang Luong, Quoc V. Le, Ilya Sutskever, Oriol Vinyals, Lukasz Kaiser   +4 more
openaire   +2 more sources