Results 61 to 70 of about 60,311 (308)
dynoGP: Deep Gaussian Processes for Dynamic System Identification
International Journal of Adaptive Control and Signal Processing, EarlyView.This work introduces a novel class of deep models for system identification, dynamical deep Gaussian processes, which combine the strengths of data‐driven methods, such as those based on neural network architectures, with the ability to output a probability distribution for uncertainty representation.
Alessio Benavoli +3 more
wiley +1 more source
Experimental Realization of a Quantum Autoencoder: The Compression of Qutrits via Machine Learning
, 2019 With quantum resources a precious commodity, their efficient use is highly desirable. Quantum autoencoders have been proposed as a way to reduce quantum memory requirements.
Pepper, Alex +2 more
core +1 more source
Unpriortized Autoencoder For Image Generation
, 2020 In this paper, we treat the image generation task using an autoencoder, a representative latent model. Unlike many studies regularizing the latent variable's distribution by assuming a manually specified prior, we approach the image generation task ...
Lee, Hojun +5 more
core +1 more source
Self‐Adaptive Gradient Interphase Enables Durable Solid‐State Lithium Metal Batteries
Advanced Functional Materials, EarlyView.This work presents a machine learning‐guided interfacial design that forms a self‐adaptive graded interphase on lithium metal anode. A B105M40 composite interlayer evolves into lithiophilic, porous, and fast‐ion‐conducting phases, enabling intimate contact, dendrite suppression, and uniform lithium deposition.
Hongmin Liu +9 more
wiley +1 more source
Evidence for Itinerant Ferromagnetic Flat Bands Producing Large Transverse Responses
Advanced Materials, EarlyView.Itinerant ferromagnetic flat bands are demonstrated in GdCo5 with a high Curie temperature of 940K, a stacked honeycomb–kagome lattice, through angle‐resolved photoemission spectroscopy and magneto‐thermoelectric measurements. These topological flat bands generate large Berry curvaturte, producing gigantic anomalous Nernst effect with record‐high ...
Susumu Minami +15 more
wiley +1 more source
, 2020 Learning the true density in high-dimensional feature spaces is a well-known problem in machine learning. In this work, we consider generative autoencoders based on maximum-mean discrepancy (MMD) and provide theoretical insights. In particular, (i) we prove that MMD coupled with Coulomb kernels has optimal convergence properties, which are similar to ...
Emanuele Sansone +2 more
openaire +3 more sources
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
The deep kernelized autoencoder [PDF]
Applied Soft Computing, 2018 Autoencoders learn data representations (codes) in such a way that the input is reproduced at the output of the network. However, it is not always clear what kind of properties of the input data need to be captured by the codes. Kernel machines have experienced great success by operating via inner-products in a theoretically well-defined reproducing ...
Michael Kampffmeyer +4 more
openaire +4 more sources
LSTM-Autoencoder Deep Learning Model for Anomaly Detection in Electric Motor
EnergiesAnomaly detection is the process of detecting unusual or unforeseen patterns or events in data. Many factors, such as malfunctioning hardware, malevolent activities, or modifications to the data’s underlying distribution, might cause anomalies.
Fadhila Lachekhab +4 more
doaj +1 more source