scholarly journals Differentiation and Decoding of the Spatial Modulations of Textures by the Multilayer Convolutional Neural Networks

Vestnik RFFI ◽  
2019 ◽  
pp. 94-104
Author(s):  
Denis V. Yavna ◽  
Vitaly V. Babenko ◽  
Alexander S. Stoletniy ◽  
Daria P. Shchetinina ◽  
Dariya S. Alekseeva
Keyword(s):  
Short Review ◽  
Second Order ◽  
Convolutional Networks ◽  
Fast Learning ◽  
Learning Classifier ◽  
Saliency Maps ◽  
Network Training ◽  
Network Approaches ◽  
Learning Architectures ◽  
Spatial Modulations

The paper constitutes a short review of the second-order visual mechanisms studies. Their contribution to the process of the visual attention controlling is being of great interest today. Basic and neural network approaches in the modeling of the second-order visual mechanisms are discussed. The authors report the results of network training when modulated textures were used as training sets, and also present, as an example, the architecture of fast-learning classifier with accuracy more than 98% on test set. The representations obtained through learning are demonstrated. The results of convolutional autoencoders’ training to extract the envelope of the textures, that are modulated in contrast, orientation, and spatial frequency, are presented as well. The successful learning architectures are given as examples. The authors assume that using of convolutional networks in the modeling of the second-order visual mechanisms provides the great perspective, while the results can be used in the algorithms of saliency maps development.

scholarly journals Calculus of constituents: A decidable fragment of second order PL

2006 ◽  
Vol 16 (1) ◽  
pp. 47-49
Author(s):  
Angelina Ilic-Stepic ◽  
Dragan Doder
Keyword(s):  
Short Review ◽  
Second Order ◽  
Decidable Fragment

We present a short review of the calculus of constituents.

scholarly journals VPNET: Variable Projection Networks

2021 ◽  
Author(s):  
Péter Kovács ◽  
Gergő Bognár ◽  
Christian Huber ◽  
Mario Huemer
Keyword(s):  
Signal Processing ◽  
Network Architecture ◽  
Computational Cost ◽  
Learning Ability ◽  
Ecg Signals ◽  
Variable Projection ◽  
Model Driven ◽  
Convolutional Networks ◽  
Fast Learning ◽  
Fully Connected

In this paper, we introduce VPNet, a novel model-driven neural network architecture based on variable projection (VP). Applying VP operators to neural networks results in learnable features, interpretable parameters, and compact network structures. This paper discusses the motivation and mathematical background of VPNet and presents experiments. The VPNet approach was evaluated in the context of signal processing, where we classified a synthetic dataset and real electrocardiogram (ECG) signals. Compared to fully connected and one-dimensional convolutional networks, VPNet offers fast learning ability and good accuracy at a low computational cost of both training and inference. Based on these advantages and the promising results obtained, we anticipate a profound impact on the broader field of signal processing, in particular on classification, regression and clustering problems.

scholarly journals Zinc(II) as a Versatile Template for Efficient Dipolar and Octupolar Second-Order Nonlinear Optical Molecular Materials §

Inorganics ◽  
2018 ◽  
Vol 6 (4) ◽  
pp. 133 ◽  
Author(s):  
Santo Di Bella ◽  
Alessia Colombo ◽  
Claudia Dragonetti ◽  
Stefania Righetto ◽  
Dominique Roberto
Keyword(s):  
Nonlinear Optical ◽  
Rayleigh Scattering ◽  
Second Harmonic ◽  
Short Review ◽  
Second Order ◽  
Donor Ligands ◽  
Molecular Materials ◽  
Nitrogen Donor Ligands ◽  
Nitrogen Donor ◽  
Zinc Coordination

This short review outlines the main results obtained in the field of molecular materials based on zinc coordination compounds for second-order nonlinear optics. It presents an overview of the main classes of second-order nonlinear optical (NLO) active complexes bearing monodentate, bidentate, tridentate, or tetradentate π-delocalized ligands such as substituted stilbazoles, bipyridines, phenanthrolines, terpyridines, and Schiff bases. Macrocyclic ligands such as porphyrins and phthalocyanines are not covered. This paper shows how coordination to the Zn(II) center of π-delocalized nitrogen donor ligands produces a significant enhancement of their quadratic hyperpolarizability. Dipolar complexes are mainly presented, but octupolar zinc complexes are also presented. The coverage is mainly focused on NLO properties that are measured at the molecular level, working in solution, by means of the electric field-induced second harmonic generation (EFISH) or the hyper-Rayleigh scattering (HRS) techniques.

scholarly journals Continuous second order minimization method with variable metric projection operator

2019 ◽  
Vol 21 (1) ◽  
pp. 34-47
Author(s):  
Valerian G. Malinov
Keyword(s):  
Metric Projection ◽  
Short Review ◽  
Second Order ◽  
Smooth Functions ◽  
Minimization Method ◽  
Variable Metric ◽  
Metric Operator ◽  
Theoretical Reasoning ◽  
Fréchet Differentiable ◽  
Variable Metric Method

The paper examines a new continuous projection second order method of minimization of continuously Frechet differentiable convex functions on the convex closed simple set in separable, normed Hilbert space with variable metric. This method accelerates common continuous projection minimization method by means of quasi-Newton matrices. In the method, apart from variable metric operator, vector of search direction for motion to minimum, constructed in auxiliary extrapolated point, is used. By other word, complex continuous extragradient variable metric method is investigated. Short review of allied methods is presented and their connections with given method are indicated. Also some auxiliary inequalities are presented which are used for theoretical reasoning of the method. With their help, under given supplemental conditions, including requirements on operator of metric and on method parameters, convergence of the method for convex smooth functions is proved. Under conditions completely identical to those in convergence theorem, without additional requirements to the function, estimates of the method's convergence rate are obtained for convex smooth functions. It is pointed out, that one must execute computational implementation of the method by means of numerical methods for ODEs solution and by taking into account the conditions of proved theorems.

scholarly journals Electroencephalogram-Based Motor Imagery Classification Using Deep Residual Convolutional Networks

2021 ◽  
Vol 15 ◽  
Author(s):  
Jing-Shan Huang ◽  
Wan-Shan Liu ◽  
Bin Yao ◽  
Zhan-Xiang Wang ◽  
Si-Fang Chen ◽  
...  
Keyword(s):  
Motor Imagery ◽  
Recognition Accuracy ◽  
Wavelet Packet ◽  
Eeg Signals ◽  
Convolutional Networks ◽  
Learning Classifier ◽  
Signal Features ◽  
Electroencephalogram Eeg ◽  
Bci System

The classification of electroencephalogram (EEG) signals is of significant importance in brain-computer interface (BCI) systems. Aiming to achieve intelligent classification of motor imagery EEG types with high accuracy, a classification methodology using the wavelet packet decomposition (WPD) and the proposed deep residual convolutional networks (DRes-CNN) is proposed. Firstly, EEG waveforms are segmented into sub-signals. Then the EEG signal features are obtained through the WPD algorithm, and some selected wavelet coefficients are retained and reconstructed into EEG signals in their respective frequency bands. Subsequently, the reconstructed EEG signals were utilized as input of the proposed deep residual convolutional networks to classify EEG signals. Finally, EEG types of motor imagination are classified by the DRes-CNN classifier intelligently. The datasets from BCI Competition were used to test the performance of the proposed deep learning classifier. Classification experiments show that the average recognition accuracy of this method reaches 98.76%. The proposed method can be further applied to the BCI system of motor imagination control.

Sign in / Sign up

Export Citation Format

Share Document