Results 31 to 40 of about 8,034,918 (294)
Predicting Parameters in Deep Learning
CoRR, 2013 We demonstrate that there is significant redundancy in the parameterization of several deep learning models. Given only a few weight values for each feature it is possible to accurately predict the remaining values. Moreover, we show that not only can the parameter values be predicted, but many of them need not be learned at all.
Denil, M +4 more
openaire +4 more sources
Constrained Parameter Inference as a Principle for Learning
Trans. Mach. Learn. Res., 2022 18 p.
Ahmad, N. +2 more
openaire +5 more sources
Frequentist parameter estimation with supervised learning [PDF]
AVS Quantum Science, 2021 Recently, there has been a great deal of interest surrounding the calibration of quantum sensors using machine learning techniques. This work explores the use of regression to infer a machine-learned point estimate of an unknown parameter. Although the analysis is necessarily frequentist—relying on repeated estimates to build up statistics—the authors ...
Samuel P. Nolan +2 more
openaire +3 more sources
The use of Bayesian network in analysis of urban intersection crashes in China
Transport, 2015 Traffic fatalities and injuries on urban roads especially at urban intersections constitute a growing problem in China. This study aims at researching urban intersection crashes in China and drawing conclusions by using hierarchical structured data with ...
Jinbao Zhao, Wei Deng
doaj +1 more source
Deep Learning Based Cognitive Radio Modulation Parameter Estimation
IEEE Access, 2023 Automatic Modulation Classification (AMC) is a critical issue in electromagnetic spatial perception. Currently traditional recognition techniques are difficult to adapt to complex signal situations.
Wenxuan Ma, Zhuoran Cai
doaj +1 more source
Adaptive Neuro-Fuzzy Fusion of Multi-Sensor Data for Monitoring a Pilot’s Workload Condition
Sensors, 2019 To realize an early warning of unbalanced workload in the aircraft cockpit, it is required to monitor the pilot’s real-time workload condition. For the purpose of building the mapping relationship from physiological and flight data to workload, a ...
Xia Zhang +4 more
doaj +1 more source
Effects of Learning Parameters on Learning Procedure and Performance of a BPNN [PDF]
Neural Networks, 1997 We examined the effects of changing learning parameters on the learning procedure and performance of back-propagation neural networks used to pick seismic arrivals. The results show that such change mainly affects the speed of convergence of the learning procedures, and does not affect the BPNN structure and its overall performance.
Hengchang Dai, Colin MacBeth
openaire +3 more sources
Online Variational Filtering and Parameter Learning
CoRR, 2021 27 pages, 6 figures.
Andrew Campbell +3 more
openaire +4 more sources
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 +6 more sources
PENILAIAN KEBUTUHAN PEMANFAATAN E-LEARNING [PDF]
, 2014 : This research aims to get a description of State University of Jakarta (UNJ) readiness to take advantage of e-learning in implementation of lecture viewed from some aspects both institutional, technological, and pedagogical.
Khaerudin Khaerudin +1 more
core +1 more source