Results 251 to 260 of about 10,742,237 (292)

Contrastive Learning with Frequency Domain for Sequential Recommendation

Applied Soft Computing Journal, 2023
Liguo Zhang, Guisheng Yin, Yuxin Dong
exaly   +3 more sources

Learned Image Compression with Frequency Domain Loss

2021 International Conference on Information Networking (ICOIN), 2021
This paper proposes an end-to-end deep image compression model with a frequency domain loss function. Unlike previous deep image compression methods, the model is computed jointly in the frequency domain. By calculating in the frequency domain, the model incorporates high-frequency components to capture detailed information in the reconstructed images ...
Soonbin Lee, JongBeom Jeong, Inae Kim, Eun-Seok Ryu   +3 more
openaire   +2 more sources

Rethinking domain-agnostic continual learning via frequency completeness learning

Information Fusion
Haitao Zhang, Peng Jian, Jing Shen
exaly   +3 more sources

Deep learning-assisted frequency-domain photoacoustic microscopy

Optics Letters, 2023
Frequency-domain photoacoustic microscopy (FD-PAM) constitutes a powerful cost-efficient imaging method integrating intensity-modulated laser beams for the excitation of single-frequency photoacoustic waves. Nevertheless, FD-PAM provides an extremely small signal-to-noise ratio (SNR), which can be up to two orders of magnitude lower than the ...
Tserevelakis, George J., Barmparis, Georgios D., Kokosalis, Nikolaos, Giosa, Eirini Smaro, Pavlopoulos, Anastasios, Tsironis, Giorgos P., Zacharakis, Giannis   +6 more
openaire   +2 more sources

Frequency domain adaptive learning feedforward control

Proceedings 2001 IEEE International Symposium on Computational Intelligence in Robotics and Automation (Cat. No.01EX515), 2002
A learning feedforward control (LFFC) acts as an "add-on" element to an existing feedback controller (FBC). The LFFC signal is updated iteratively based on the output of a B-splines network (BSN), with the FBC signal of previous iteration as its input. There are only two parameters to tune: the B-spline support width d and the learning gain /spl gamma/.
YangQuan Chen, Kevin L. Moore 0001
openaire   +1 more source

Parametric Iterative Learning Control in the time and frequency domain

International Journal of Intelligent Systems Technologies and Applications, 2007
For the control of cyclic processes Iterative Learning Control (ILC) has been proven to be an efficient concept. In this contribution a parametric framework is proposed that uses an analogy to a discrete time control loop and intentionally avoids highly theoretical concepts such as two dimensional systems theory.
Hellmar Rockel, Ulrich Konigorski
openaire   +3 more sources

Frequency domain analysis of learning systems

Proceedings of the 27th IEEE Conference on Decision and Control, 2003
Frequency domain arguments on a general learning law are presented to verify claims of convergence which relax earlier requirements on the learning law transfer function. Known convergence properties are used to develop a pole-placement interpretation for an example for which simulations using a proportional-derivative learning law form are carried out.
L.M. Hideg, R.P. Judd
openaire   +1 more source

Filter Pruning via Learned Representation Median in the Frequency Domain

IEEE Transactions on Cybernetics, 2023
In this article, we propose a novel filter pruning method for deep learning networks by calculating the learned representation median (RM) in frequency domain (LRMF). In contrast to the existing filter pruning methods that remove relatively unimportant filters in the spatial domain, our newly proposed approach emphasizes the removal of absolutely ...
Xin Zhang 0092, Weiying Xie, Yunsong Li 0001, Jie Lei 0001, Qian Du 0001   +4 more
openaire   +2 more sources

A Frequency Domain Analysis of Learning Control

Journal of Dynamic Systems, Measurement, and Control, 1994
The convergence of learning control is traditionally analyzed in the time domain. This is because a finite planning horizon is often assumed and the analysis in time domain can be extended to time-varying and nonlinear systems. For linear time-invariant (LTI) systems with infinite planning horizon, however, we show that simple frequency domain ...
openaire   +2 more sources

A FREQUENCY-DOMAIN MODEL FOR E-LEARNING

eLearning and Software for Education, 2020
The characteristics of e-learning make it suitable to the Systems Theory approach. A system is an ensemble of entities which interact among themselves and with the exterior, in order to reach an objective. Clearly, e-learning integrates with this definition.
openaire   +1 more source