<abstract xmlns="http://www.w3.org/1999/xhtml">In this research note the satisficing newsvendor problem is considered which is defined as the maximization of the probability of exceeding the expected profit multiplied by a positive constant. This constant called optimism coefficient can be chosen by the firm’s management either based on their preference or the market conditions. The coefficient indicates whether there is a low or high optimistic decision maker. For the general demand distribution the results are significantly dependent on this coefficient.</abstract>

Satisficing Newsvendor Problem with the Optimism Coefficient

<abstract xmlns="http://www.w3.org/1999/xhtml">This paper addresses the problem of effective processing using third generation neural networks. The article features two new models of spiking neurons based on the cusp catastrophe theory. The effectiveness of the models is demonstrated with an example of a network composed of three neurons solving the problem of linear inseparability of the XOR function. The proposed solutions are dedicated to hardware implementation using the Edge computing strategy. The paper presents simulation results and outlines further research direction in the field of practical applications and implementations using nanometer CMOS technologies and the current processing mode.</abstract>

Spiking Neural Network Based on Cusp Catastrophe Theory

<abstract xmlns="http://www.w3.org/1999/xhtml">A novel technique for deep learning of image classifiers is presented. The learned CNN models higher offer better separation of deep features (also known as embedded vectors) measured by Euclidean proximity and also no deterioration of the classification results by class membership probability. The latter feature can be used for enhancing image classifiers having the classes at the model’s exploiting stage different from from classes during the training stage. While the Shannon information of SoftMax probability for target class is extended for mini-batch by the intra-class variance, the trained network itself is extended by the Hadamard layer with the parameters representing the class centers. Contrary to the existing solutions, this extra neural layer enables interfacing of the training algorithm to the standard stochastic gradient optimizers, e.g. AdaM algorithm. Moreover, this approach makes the computed centroids immediately adapting to the updating embedded vectors and finally getting the comparable accuracy in less epochs.</abstract>

On Intra-Class Variance for Deep Learning of Classifiers

<abstract xmlns="http://www.w3.org/1999/xhtml">Convolutional neural networks (CNN) is a contemporary technique for computer vision applications, where pooling implies as an integral part of the deep CNN. Besides, pooling provides the ability to learn invariant features and also acts as a regularizer to further reduce the problem of overfitting. Additionally, the pooling techniques significantly reduce the computational cost and training time of networks which are equally important to consider. Here, the performances of pooling strategies on different datasets are analyzed and discussed qualitatively. This study presents a detailed review of the conventional and the latest strategies which would help in appraising the readers with the upsides and downsides of each strategy. Also, we have identified four fundamental factors namely network architecture, activation function, overlapping and regularization approaches which immensely affect the performance of pooling operations. It is believed that this work would help in extending the scope of understanding the significance of CNN along with pooling regimes for solving computer vision problems.</abstract>

Implications of Pooling Strategies in Convolutional Neural Networks: A Deep Insight

<abstract xmlns="http://www.w3.org/1999/xhtml">In the presented research two Deep Neural Network (DNN) models for face image analysis were developed. The first one detects eyes, nose and mouth and it is based on a moderate size Convolutional Neural Network (CNN) while the second one identifies 68 landmarks resulting in a novel Face Alignment Network composed of a CNN and a recurrent neural network. The Face Parts Detector inputs face image and outputs the pixel coordinates of bounding boxes for detected facial parts. The Face Alignment Network extracts deep features in CNN module while in the recurrent module it generates 68 facial landmarks using not only this deep features, but also the geometry of facial parts. Both methods are robust to varying head poses and changing light conditions.</abstract>

Institute of Radioelectronics and Multimedia Technology

Convolutional and Recurrent Neural Networks for Face Image Analysis

AHEAD OF PRINT

Volume 49 (2024): Issue 1 (February 2024)

Volume 48 (2023): Issue 4 (December 2023)

Volume 48 (2023): Issue 3 (September 2023)

Volume 48 (2023): Issue 2 (June 2023)

Volume 48 (2023): Issue 1 (March 2023)

Volume 47 (2022): Issue 4 (December 2022) Special issue: “Recent advances on supply chain network design”

Volume 47 (2022): Issue 3 (September 2022)

Volume 47 (2022): Issue 2 (June 2022)

Volume 47 (2022): Issue 1 (February 2022)

Volume 46 (2021): Issue 4 (December 2021)

Volume 46 (2021): Issue 3 (September 2021)

Volume 46 (2021): Issue 2 (June 2021)

Volume 46 (2021): Issue 1 (March 2021)

Volume 45 (2020): Issue 4 (December 2020)

Volume 45 (2020): Issue 3 (September 2020)

Volume 45 (2020): Issue 2 (June 2020)

Volume 45 (2020): Issue 1 (March 2020)

Volume 44 (2019): Issue 4 (December 2019)

Volume 44 (2019): Issue 3 (September 2019)

Volume 44 (2019): Issue 2 (June 2019)

Volume 44 (2019): Issue 1 (March 2019)

Volume 43 (2018): Issue 4 (December 2018)

Volume 43 (2018): Issue 3 (September 2018)

Volume 43 (2018): Issue 2 (June 2018)

Volume 43 (2018): Issue 1 (March 2018)

Volume 42 (2017): Issue 4 (December 2017)

Volume 42 (2017): Issue 3 (September 2017)

Volume 42 (2017): Issue 2 (June 2017)

Volume 42 (2017): Issue 1 (February 2017)

Volume 41 (2016): Issue 4 (November 2016)

Volume 41 (2016): Issue 3 (September 2016)

Volume 41 (2016): Issue 2 (June 2016)

Volume 41 (2016): Issue 1 (March 2016)

Volume 40 (2015): Issue 4 (December 2015)

Volume 40 (2015): Issue 3 (September 2015)

Volume 40 (2015): Issue 2 (June 2015)

Volume 40 (2015): Issue 1 (March 2015)

Volume 39 (2014): Issue 4 (December 2014)

Volume 39 (2014): Issue 3 (July 2014)

Volume 39 (2014): Issue 2 (June 2014)

Volume 39 (2014): Issue 1 (February 2014)

Volume 38 (2013): Issue 4 (December 2013)

Volume 38 (2013): Issue 3 (September 2013)

Volume 38 (2013): Issue 2 (June 2013)

Volume 38 (2013): Issue 1 (March 2013)

Volume 37 (2012): Issue 4 (December 2012)

Volume 37 (2012): Issue 3 (October 2012)

Volume 37 (2012): Issue 2 (June 2012)

Volume 37 (2012): Issue 1 (March 2012)

Foundations of Computing and Decision Sciences

ISSN: 0867-6356 (print version)  Foundations of Computing and Decision Sciences (until 1990 Foundations of Control Engineering) is a quarterly peer-reviewed international journal published since 1975. One of its main aims is its focus on the links between Computing (understood in the sense defined in the report of the ACM Task Force on the Core of Computer Science chaired by Peter J. Denning: Computing as a Discipline, CACM, Vol. 32, No. 1, 1989) and broadly understood Decision Sciences.  Scope of topics  The journal provides a forum for exchange of ideas for researchers in the fields of computing and decision sciences. The scope of the journal covers various areas of computing and decision sciences, particularly:    approximate reasoning,  artificial intelligence,  combinatorial optimization,  computational complexity theory,  databases and data warehouses,  intelligent decision support,  knowledge engineering,  machine learning and data mining,  metaheuristics,  multiple criteria decision analysis,  networking and distributed systems,  parallel computing and concurrency,  production and project scheduling,  scheduling theory,  soft and granular computing,  software engineering.     Why submit   International editorial board composed of distinguished scholars highly representative of the field of computing and decision sciences,  Quick turnaround,  Comprehensive peer review with at least two highly competent referees assessing each manuscript,  Promotion of published papers in the vast scientific community of researchers working in the field.   Rejection Rate   ca. 60%   Archiving  Sciendo archives the contents of this journal in Portico - digital long-term preservation service of scholarly books, journals and collections.  Plagiarism policy  The editorial board is participating in a growing community of Similarity Check System's users in order to ensure that the content published is original and trustworthy. Similarity Check is a medium that allows for comprehensive manuscripts screening, aimed to eliminate plagiarism and provide a high standard and quality peer-review process (iThenticate, https://www.ithenticate.com/ ). 