Results 61 to 70 of about 201,968 (266)

Bayesian Reinforcement Learning via Deep, Sparse Sampling

, 2020
We address the problem of Bayesian reinforcement learning using efficient model-based online planning. We propose an optimism-free Bayes-adaptive algorithm to induce deeper and sparser exploration with a theoretical bound on its performance relative to ...
Basu, Debabrota, Dimitrakakis, Christos, Grover, Divya   +2 more
core  

Self‐Assembled Monolayers in p–i–n Perovskite Solar Cells: Molecular Design, Interfacial Engineering, and Machine Learning–Accelerated Material Discovery

Advanced Materials, EarlyView.
This review highlights the role of self‐assembled monolayers (SAMs) in perovskite solar cells, covering molecular engineering, multifunctional interface regulation, machine learning (ML) accelerated discovery, advanced device architectures, and pathways toward scalable fabrication and commercialization for high‐efficiency and stable single‐junction and
Asmat Ullah, Ying Luo, Stefaan De Wolf
wiley   +1 more source

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

Deep Bayesian Active Learning with Image Data

, 2017
Even though active learning forms an important pillar of machine learning, deep learning tools are not prevalent within it. Deep learning poses several difficulties when used in an active learning setting. First, active learning (AL) methods generally rely on being able to learn and update models from small amounts of data.
Ghahramani, Z, Gal, Y, Islam, R
openaire   +3 more sources

Bayesian Deep Learning via Subnetwork Inference

Proceedings of Machine Learning Research, 2020
The Bayesian paradigm has the potential to solve core issues of deep neural networks such as poor calibration and data inefficiency. Alas, scaling Bayesian inference to large weight spaces often requires restrictive approximations. In this work, we show that it suffices to perform inference over a small subset of model weights in order to obtain ...
Daxberger, E., Nalisnick, E., Allingham, J.U., Antorán, J., Hernández-Lobato, J.M.   +4 more
openaire   +4 more sources

A Hybrid Deep Learning Model for Link Dynamic Vehicle Count Forecasting with Bayesian Optimization

Journal of Advanced Transportation, 2023
The link dynamic vehicle count is a spatial variable that measures the traffic state of road sections, which reflects the actual traffic demand. This paper presents a hybrid deep learning method that combines the gated recurrent unit (GRU) neural network
Chunguang He, Dianhai Wang, Yi Yu, Zhengyi Cai   +3 more
doaj   +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

Nanomaterial Integration at Liquid–Liquid Interfaces for Green Catalysis

Advanced Materials, EarlyView.
Functional nanomaterials assembled at liquid–liquid interfaces create dual‐role platforms serving as emulsion stabilizers and catalytic sites, offering enhanced reaction kinetics with improved catalyst recovery and recyclability. This review examines design strategies, structure‐performance relationships, and industrial implementation prospects of ...
Bokgi Seo, Jaewon Shin, Minkyoung Jang, Kyoungho Choi, Tengfei Pang, Fangrui Zhong, Jin Woong Kim   +6 more
wiley   +1 more source

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

Modeling of moral decisions with deep learning

Visual Computing for Industry, Biomedicine, and Art, 2020
One example of an artificial intelligence ethical dilemma is the autonomous vehicle situation presented by Massachusetts Institute of Technology researchers in the Moral Machine Experiment.
Christopher Wiedeman, Ge Wang, Uwe Kruger   +2 more
doaj   +1 more source