Volume 13 (2023): Edition 2 (March 2023)

This paper presents a parallel approach to the Levenberg-Marquardt algorithm (LM). The use of the Levenberg-Marquardt algorithm to train neural networks is associated with significant computational complexity, and thus computation time. As a result, when the neural network has a big number of weights, the algorithm becomes practically ineffective. This article presents a new parallel approach to the computations in Levenberg-Marquardt neural network learning algorithm. The proposed solution is based on vector instructions to effectively reduce the high computational time of this algorithm. The new approach was tested on several examples involving the problems of classification and function approximation, and next it was compared with a classical computational method. The article presents in detail the idea of parallel neural network computations and shows the obtained acceleration for different problems.

One of the fundamental issues of modern society is access to interesting and useful content. As the amount of available content increases, this task becomes more and more challenging. Our needs are not always formulated in words; sometimes we have to use complex data types like images. In this paper, we consider the three approaches to creating recommender systems based on image data. The proposed systems are evaluated on a real-world dataset. Two case studies are presented. The first one presents the case of an item with many similar objects in a database, and the second one with only a few similar items.

Recommendation algorithms trained on a training set containing sub-optimal decisions may increase the likelihood of making more bad decisions in the future. We call this harmful effect self-induced bias, to emphasize that the bias is driven directly by the user’s past choices. In order to better understand the nature of self-induced bias of recommendation algorithms that are used by older adults with cognitive limitations, we have used agent-based simulation. Based on state-of-the-art results in psychology of aging and cognitive science, as well as our own empirical results, we have developed a cognitive model of an e-commerce client that incorporates cognitive decision-making abilities. We have evaluated the magnitude of self-induced bias by comparing results achieved by simulated agents with and without cognitive limitations due to age. We have also proposed new recommendation algorithms designed to counteract self-induced bias. The algorithms take into account user preferences and cognitive abilities relevant to decision making. To evaluate the algorithms, we have introduced 3 benchmarks: a simple product filtering method and two types of widely used recommendation algorithms: Content-Based and Collaborative filtering. Results indicate that the new algorithms outperform benchmarks both in terms of increasing the utility of simulated agents (both old and young), and in reducing self-induced bias.

Scanning real 3D objects face many technical challenges. Stationary solutions allow for accurate scanning. However, they usually require special and expensive equipment. Competitive mobile solutions (handheld scanners, LiDARs on vehicles, etc.) do not allow for an accurate and fast mapping of the surface of the scanned object. The article proposes an end-to-end automated solution that enables the use of widely available mobile and stationary scanners. The related system generates a full 3D model of the object based on multiple depth sensors. For this purpose, the scanned object is marked with markers. Markers type and positions are automatically detected and mapped to a template mesh. The reference template is automatically selected for the scanned object, which is then transformed according to the data from the scanners with non-rigid transformation. The solution allows for the fast scanning of complex and varied size objects, constituting a set of training data for segmentation and classification systems of 3D scenes. The main advantage of the proposed solution is its efficiency, which enables real-time scanning and the ability to generate a mesh with a regular structure. It is critical for training data for machine learning algorithms. The source code is available at https://github.com/SATOffice/improved_scanner3D.

Modularity is a feature of most small, medium and large–scale living organisms that has evolved over many years of evolution. A lot of artificial systems are also modular, however, in this case, the modularity is the most frequently a consequence of a handmade design process. Modular systems that emerge automatically, as a result of a learning process, are very rare. What is more, we do not know mechanisms which result in modularity. The main goal of the paper is to continue the work of other researchers on the origins of modularity, which is a form of optimal organization of matter, and the mechanisms that led to the spontaneous formation of modular living forms in the process of evolution in response to limited resources and environmental variability. The paper focuses on artificial neural networks and proposes a number of mechanisms operating at the genetic level, both those borrowed from the natural world and those designed by hand, the use of which may lead to network modularity and hopefully to an increase in their effectiveness. In addition, the influence of external factors on the shape of the networks, such as the variability of tasks and the conditions in which these tasks are performed, is also analyzed. The analysis is performed using the Hill Climb Assembler Encoding constructive neuro-evolutionary algorithm. The algorithm was extended with various module-oriented mechanisms and tested under various conditions. The aim of the tests was to investigate how individual mechanisms involved in the evolutionary process and factors external to this process affect modularity and efficiency of neural networks.