All issues

This paper presents the results of experimental validation of some structural issues concerning the practical use of methods to overcome catastrophic forgetting of neural networks. A comparison of current effective methods like EWC (Elastic Weight Consolidation) and WVA (Weight Velocity Attenuation) is made and their advantages and disadvantages are considered. It is shown that EWC is better for tasks where full retention of learned skills is required on all the tasks in the training queue, while WVA is more suitable for sequential tasks with very limited computational resources, or when reuse of representations and acceleration of learning from task to task is required rather than exact retention of the skills. The attenuation of the WVA method must be applied to the optimization step, i. e. to the increments of neural network weights, rather than to the loss function gradient itself, and this is true for any gradient optimization method except the simplest stochastic gradient descent (SGD). The choice of the optimal weights attenuation function between the hyperbolic function and the exponent is considered. It is shown that hyperbolic attenuation is preferable because, despite comparable quality at optimal values of the hyperparameter of the WVA method, it is more robust to hyperparameter deviations from the optimal value (this hyperparameter in the WVA method provides a balance between preservation of old skills and learning a new skill). Empirical observations are presented that support the hypothesis that the optimal value of this hyperparameter does not depend on the number of tasks in the sequential learning queue. And, consequently, this hyperparameter can be picked up on a small number of tasks and used on longer sequences.

Solution of Dynamic Light Scattering problem makes it possible to determine particle size distribution (PSD) from the spectrum of the intensity of scattered light. As a result of experiment, an intensity curve is obtained. The experimentally obtained spectrum of intensity is compared with the theoretically expected spectrum, which is the Lorentzian line. The main task is to determine on the basis of these data the relative concentrations of particles of each class presented in the solution. The article presents a method for constructing and using a neural network trained on synthetic data to determine PSD in a solution in the range of 1–500 nm. The neural network has a fully connected layer of 60 neurons with the RELU activation function at the output, a layer of 45 neurons and the same activation function, a dropout layer and 2 layers with 15 and 1 neurons (network output). The article describes how the network has been trained and tested on synthetic and experimental data. On the synthetic data, the standard deviation metric (rmse) gave a value of 1.3157 nm. Experimental data were obtained for particle sizes of 200 nm, 400 nm and a solution with representatives of both sizes. The results of the neural network and the classical linear methods are compared. The disadvantages of the classical methods are that it is difficult to determine the degree of regularization: too much regularization leads to the particle size distribution curves are much smoothed out, and weak regularization gives oscillating curves and low reliability of the results. The paper shows that the neural network gives a good prediction for particles with a large size. For small sizes, the prediction is worse, but the error quickly decreases as the particle size increases.

The paper provides a method for selecting the composition of a refrigerant with a given isobaric cooling curve using an artificial neural network (ANN). This method is based on the use of 1D layers of a convolutional neural network. To train the neural network, we applied a technological model of a simple heat exchanger in the UniSim design program, using the Peng – Robinson equation of state.We created synthetic database on isobaric boiling curves of refrigerants of different compositions using the technological model. To record the database, an algorithm was developed in the Python programming language, and information on isobaric boiling curves for 1 049 500 compositions was uploaded using the COM interface. The compositions have generated by Monte Carlo method. Designed architecture of ANN allows select composition of a mixed refrigerant by 101 points of boiling curve. ANN gives mole flows of mixed refrigerant by composition (methane, ethane, propane, nitrogen) on the output layer. For training ANN, we used method of cyclical learning rate. For results demonstration we selected MR composition by natural gas cooling curve with a minimum temperature drop of 3 К and a maximum temperature drop of no more than 10 К, which turn better than we predicted via UniSim SQP optimizer and better than predicted by $k$-nearest neighbors algorithm. A significant value of this article is the fact that an artificial neural network can be used to select the optimal composition of the refrigerant when analyzing the cooling curve of natural gas. This method can help engineers select the composition of the mixed refrigerant in real time, which will help reduce the energy consumption of natural gas liquefaction.

When recognizing workers on images of a construction site obtained from surveillance cameras, a situation is typical in which the objects of detection have a very different spatial scale relative to each other and other objects. An increase in the accuracy of detection of small objects can be achieved by using the Feature-Fused modification of the SSD detector. Together with the use of overlapping image slicing on the inference, this model copes well with the detection of small objects. However, the practical use of this approach requires manual adjustment of the slicing parameters. This reduces the accuracy of object detection on scenes that differ from the scenes used in training, as well as large objects. In this paper, we propose an algorithm for automatic selection of image slicing parameters depending on the ratio of the characteristic geometric dimensions of objects in the image. We have developed a two-pass version of the Feature-Fused SSD detector for automatic determination of optimal image slicing parameters. On the first pass, a fast truncated version of the detector is used, which makes it possible to determine the characteristic sizes of objects of interest. On the second pass, the final detection of objects with slicing parameters selected after the first pass is performed. A dataset was collected with images of workers on a construction site. The dataset includes large, small and diverse images of workers. To compare the detection results for a one-pass algorithm without splitting the input image, a one-pass algorithm with uniform splitting, and a two-pass algorithm with the selection of the optimal splitting, we considered tests for the detection of separately large objects, very small objects, with a high density of objects both in the foreground and in the background, only in the background. In the range of cases we have considered, our approach is superior to the approaches taken in comparison, allows us to deal well with the problem of double detections and demonstrates a quality of 0.82–0.91 according to the mAP (mean Average Precision) metric.

This paper proposes an architectural solution for organizing a convolutional neural network (CNN) oriented towards hardware implementation on edge devices under limited resources. To this goal, an approach to compressing spectrograms to a given size (28 × 28) is proposed using discretization, monoconversion, windowed Fourier transform, and two-dimensional interpolation. A balanced convolution procedure is developed based on compact convolutional filters, the size of which provides the balance between computational complexity and accuracy required for edge devices. An algorithm that enables convolution operations and calculation of the error function gradient in the convolutional layer in a single cycle ensuring increased performance in both inference and training modes of the CNN is proposed. The tradeoff between network trainability and its resistance to overfitting is optimized by applying the Dropout regularization method with a dropout coefficient of 0.5 for the fully connected layer.

The effectiveness of the proposed solution was demonstrated using the example of recognizing audio spectrograms of car and airplane engine sounds. The CNN was trained on a balanced dataset consisting of 7160 audio recordings. The trained network demonstrated high recognition accuracy (95%), low loss values (< 0.2), and balanced precision/recall/F-metric, demonstrating the effectiveness of the developed CNN model.

Results obtained during practical training session on MPI during high perfomance computing summer school MIPT-2010 are discussed. MPI technology were one of technologies proposed to participants for realization of project. 3D version of Conway’s Game of Life was proposed as a project. Algorithms used in the development, theoretical and practical assessment of their scalability is analyzed.

In today’s technology-driven world, lite devices like Internet of Things (IoT) devices and microcontrollers (MCUs) are becoming increasingly common. These devices are more energyefficient and affordable, often with reduced features compared to the standard versions such as very limited memory and processing power for typical machine learning models. However, modern machine learning models can have millions of parameters, resulting in a large memory footprint. This complexity not only makes it difficult to deploy these large models on resource constrained devices but also increases the risk of latency and inefficiency in processing, which is crucial in some cases where real-time responses are required such as autonomous driving and medical diagnostics. In recent years, neural networks have seen significant advancements in model optimization techniques that help deployment and inference on these small devices. This narrative review offers a thorough examination of the progression and latest developments in neural network optimization, focusing on key areas such as quantization, pruning, knowledge distillation, and neural architecture search. It examines how these algorithmic solutions have progressed and how new approaches have improved upon the existing techniques making neural networks more efficient. This review is designed for machine learning researchers, practitioners, and engineers who may be unfamiliar with these methods but wish to explore the available techniques. It highlights ongoing research in optimizing networks for achieving better performance, lowering energy consumption, and enabling faster training times, all of which play an important role in the continued scalability of neural networks. Additionally, it identifies gaps in current research and provides a foundation for future studies, aiming to enhance the applicability and effectiveness of existing optimization strategies.

The key problems of remote forest pathology monitoring for coniferous forests affected by insect pests have been analyzed. It has been demonstrated that addressing these tasks requires the use of multiclass classification results for coniferous trees in high- and ultra-high-resolution images, which are promptly obtained through monitoring via satellites or unmanned aerial vehicles (UAVs). An analytical review of modern models and methods for multiclass classification of coniferous forest images was conducted, leading to the development of three fully convolutional neural network models: Mo-U-Net, At-Mo-U-Net, and Res-Mo-U-Net, all based on the classical U-Net architecture. Additionally, the Segformer transformer model was modified to suit the task. For RGB images of fir trees Abies sibirica affected by the four-eyed bark beetle Polygraphus proximus, captured using a UAV-mounted camera, two datasets were created: the first dataset contains image fragments and their corresponding reference segmentation masks sized 256 × 256 × 3 pixels, while the second dataset contains fragments sized 480 × 480 × 3 pixels. Comprehensive studies were conducted on each trained neural network model to evaluate both classification accuracy for assessing the degree of damage (health status) of Abies sibirica trees and computation speed using test datasets from each set. The results revealed that for fragments sized 256 × 256 × 3 pixels, the At-Mo-U-Net model with an attention mechanism is preferred alongside the Modified Segformer model. For fragments sized 480 × 480 × 3 pixels, the Res-Mo-U-Net hybrid model with residual blocks demonstrated superior performance. Based on classification accuracy and computation speed results for each developed model, it was concluded that, for production-scale multiclass classification of affected fir trees, the Res-Mo-U-Net model is the most suitable choice. This model strikes a balance between high classification accuracy and fast computation speed, meeting conflicting requirements effectively.

The paper presents a hybrid artificial neural network model based on an architecture that incorporates a convolutional image encoder (CNN) and an attention module (Attention-based Multiple Instance Learning, Attention MIL). This module aggregates informative features from a sequence of frames capturing the flame spraying process. Additional technological parameters—air pressure, propane pressure, and standoff distance — are integrated into the model via a tabular channel, enabling it to account for the relationship between visual data and numerical process regime characteristics. The software implementation was developed using the Streamlit platform and the PyTorch library. It features an interactive interface for model training and result visualization, analysis of attention weights across frames, and a prediction mode for output characteristics: surface roughness ($R_a$) and the mass of the deposited coating ($m$). Experimental studies were conducted on data from real-world technological processes, and a comparative analysis of the accuracy of various model configurations was performed. The results demonstrate that the hybrid neural network, which combines visual and tabular features, achieves higher prediction accuracy compared to models using only a single modality. Furthermore, when comparing different implementations of the hybrid network, it was established that using the attention mechanism to process the series of flame spray images provides a significant increase in accuracy over a simple averaging of features without attention. The application includes an attention visualization module that creates a montage of the most significant frames and displays their attention weights, allowing users to identify which frames had the greatest influence on the prediction. The model’s capability for export to the ONNX format for integration into process control systems is also demonstrated. The proposed approach showcases the effectiveness of fusing visual and tabular information for manufacturing process monitoring tasks. The model can serve as a foundation for developing a decision support system or an automated quality control system for coatings produced by flame spraying. The limitations of the implemented model and prospects for its further development are also considered.

In this article the experience of reading “CUDA and OpenCL programming” course during high perfomance computing summer school MIPT-2010 is analyzed. Content of lectures and practical tasks, as well as manner of presenting of the material are regarded. Performance issues of different algorithms implemented by students at practical training session are dicussed.