Results 81 to 90 of about 190,737 (267)

Deep active learning for multi label text classification

Scientific Reports
Given a set of labels, multi-label text classification (MLTC) aims to assign multiple relevant labels for a text. Recently, deep learning models get inspiring results in MLTC.
Qunbo Wang, Hangu Zhang, Wentao Zhang, Lin Dai, Yu Liang, Haobin Shi   +5 more
doaj   +1 more source

Active User Identification Based on Asynchronous Sparse Bayesian Learning With SVM

IEEE Access, 2019
In this paper, an asynchronous sparse Bayesian learning (ASBL) algorithm-based receiver for uplink (UL) grant-free transmission is proposed. The time-domain channel estimation is performed by the ASBL algorithm to obtain the channel impulse response (CIR)
Jingwei Fu, Gang Wu, Yizhong Zhang, Lijun Deng, Shu Fang   +4 more
doaj   +1 more source

Active Bayesian Optimization: Minimizing Minimizer Entropy [PDF]

, 2012
The ultimate goal of optimization is to find the minimizer of a target function.However, typical criteria for active optimization often ignore the uncertainty about the minimizer.
Nassar, Marcel, Park, Il Memming, Park, Mijung   +2 more
core  

Robustness of Bayesian Pool-based Active Learning Against Prior Misspecification

, 2016
We study the robustness of active learning (AL) algorithms against prior misspecification: whether an algorithm achieves similar performance using a perturbed prior as compared to using the true prior.
Cuong, Nguyen Viet, Lee, Wee Sun, Ye, Nan   +2 more
core   +1 more source

Bayesian Active Learning for Sensitivity Analysis [PDF]

, 2006
Designs of micro electro-mechanical devices need to be robust against fluctuations in mass production. Computer experiments with tens of parameters are used to explore the behavior of the system, and to compute sensitivity measures as expectations over the input distribution.
openaire   +2 more sources

Data‐Driven Discovery of Quaternary Ammonium Interlayers for Efficient and Thermally Stable Perovskite Solar Cells

Advanced Materials, EarlyView.
An active learning framework, grounded in independently generated in‐house experimental data, enables reliable discovery of high‐performance interfacial materials for perovskite solar cells. Iterative model refinement autonomously converges toward structurally robust quaternary ammonium architectures, establishing a new design principle for interfacial
Jongbeom Kim, Yang Jeong Park, Chaehoon Jeon, Nahye Shin, Jaewang Park, Seungun Lee, Jino Im, Sungroh Yoon, Sang Il Seok   +8 more
wiley   +1 more source

Bayesian Dark Knowledge [PDF]

, 2015
We consider the problem of Bayesian parameter estimation for deep neural networks, which is important in problem settings where we may have little data, and/ or where we need accurate posterior predictive densities, e.g., for applications involving ...
Korattikara, Anoop, Murphy, Kevin, Rathod, Vivek, Welling, Max   +3 more
core   +1 more source

Neuromorphic Electronics for Intelligence Everywhere: Emerging Devices, Flexible Platforms, and Scalable System Architectures

Advanced Materials, EarlyView.
The perspective presents an integrated view of neuromorphic technologies, from device physics to real‐time applicability, while highlighting the necessity of full‐stack co‐optimization. By outlining practical hardware‐level strategies to exploit device behavior and mitigate non‐idealities, it shows pathways for building efficient, scalable, and ...
Kapil Bhardwaj, Roshni Satheesh Babu, Yuxin Xia, Eva Bestelink, Radu Sporea, Nikos Hastas, Ioannis Zeimpekis, Dimitra G. Georgiadou, Sayani Majumdar   +8 more
wiley   +1 more source

Structure Learning in Coupled Dynamical Systems and Dynamic Causal Modelling [PDF]

, 2019
Identifying a coupled dynamical system out of many plausible candidates, each of which could serve as the underlying generator of some observed measurements, is a profoundly ill posed problem that commonly arises when modelling real world phenomena.
Friston, Karl, Jafarian, Amirhossein, Litvak, Vladimir, Zeidman, Peter   +3 more
core   +1 more source

Magnetic Textiles: A Review of Materials, Fabrication, Properties, and Applications

Advanced Materials Technologies, EarlyView.
Magnetic textiles (M‐textiles) are emerging as a programmable materials platform that merges magnetic matter with hierarchical textile structures. This article consolidates magnetic material classes, textile architectures, and fabrication and magnetization strategies, revealing structure–property–function relationships that govern magneto‐mechanical ...
Li Ke, Moses Kumi, Xiaoming Tao, Junhong Pu   +3 more
wiley   +1 more source