Results 21 to 30 of about 1,421,625 (273)
Federated learning with hyper-parameter optimization
Journal of King Saud University: Computer and Information Sciences, 2023 Federated Learning is a new approach for distributed training of a deep learning model on data scattered across a large number of clients while ensuring data privacy.
Majid Kundroo, Taehong Kim
doaj +1 more source
Test–retest reliability of reinforcement learning parameters [PDF]
Behavior Research Methods, 2023 AbstractIt has recently been suggested that parameter estimates of computational models can be used to understand individual differences at the process level. One area of research in which this approach, called computational phenotyping, has taken hold is computational psychiatry.
Jessica Vera Schaaf +3 more
openaire +4 more sources
IEEE Access, 2020 The sensor-based human activity recognition has been wildly applied in behavior tracking, health monitoring, indoor localization etc. Using activity continuity to assist activity recognition is an important research issue, in which the activity ...
Changhai Wang +5 more
doaj +1 more source
IEEE Access, 2022 Introducing parameter constraints has become a mainstream approach for learning Bayesian network parameters with small datasets. The QMAP (Qualitative Maximum a Posteriori) estimation has produced the best learning accuracy among existing learning ...
Ruohai Di +3 more
doaj +1 more source
Learning physical parameters from dynamic scenes [PDF]
Cognitive Psychology, 2018 Humans acquire their most basic physical concepts early in development, and continue to enrich and expand their intuitive physics throughout life as they are exposed to more and varied dynamical environments. We introduce a hierarchical Bayesian framework to explain how people can learn physical parameters at multiple levels.
Ullman, Tomer D. +3 more
openaire +5 more sources
Active learning BSM parameter spaces
European Physical Journal C: Particles and Fields, 2023 Active learning (AL) has interesting features for parameter scans of new models. We show on a variety of models that AL scans bring large efficiency gains to the traditionally tedious work of finding boundaries for BSM models.
Mark D. Goodsell, Ari Joury
doaj +1 more source
Construction and Reasoning Approach of Belief Rule-Base for Classification Base on Decision Tree
IEEE Access, 2020 The classical belief rule-based (BRB) systems are usually constructed by arranging and combining referential values of antecedent attributes or by setting special fixed values, which can lead to overly large size of BRB systems in complex problems.
Yanggeng Fu +4 more
doaj +1 more source
Manifold learning for parameter reduction
Journal of Computational Physics, 2019 Large scale dynamical systems (e.g. many nonlinear coupled differential equations) can often be summarized in terms of only a few state variables (a few equations), a trait that reduces complexity and facilitates exploration of behavioral aspects of otherwise intractable models.
Holiday, Alexander +5 more
openaire +5 more sources
Research on Intelligent Maneuvering Decision-Making in Close Air Combat Based on Deep Q Network [PDF]
Hangkong bingqi, 2023 Aiming at the problem of UCAV maneuvering decision-making in close air combat, the design of reinforcement learning reward function and the selection of hyper-parameters are studied based on the framework of deep Q network algorithm.
Zhang Tingyu, Sun Mingwei, Wang Yongshuai, Chen Zengqiang
doaj +1 more source
Parameter learning in production economies
Journal of Monetary Economics, 2018 We examine how parameter learning amplifies the impact of macroeconomic shocks on equity prices and quantities in a standard production economy where a representative agent has Epstein-Zin preferences. An investor observes technology shocks which follow a regime-switching process but does not know the underlying model parameters governing the short ...
Mykola Babiak, Roman Kozhan
openaire +1 more source