Recently, due to rapid development of information and communication technologies, the data are created and consumed in the avalanche way. Distributed computing create preconditions for analyzing and processing such Big Data by distributing the computations among a number of compute nodes. In this work, performance of distributed computing environments on the basis of Hadoop and Spark frameworks is estimated for real and virtual versions of clusters. As a test task, we chose the classic use case of word counting in texts of various sizes. It was found that the running times grow very fast with the dataset size and faster than a power function even. As to the real and virtual versions of cluster implementations, this tendency is the similar for both Hadoop and Spark frameworks. Moreover, speedup values decrease significantly with the growth of dataset size, especially for virtual version of cluster configuration. The problem of growing data generated by IoT and multimodal (visual, sound, tactile, neuro and brain-computing, muscle and eye tracking, etc.) interaction channels is presented. In the context of this problem, the current observations as to the running times and speedup on Hadoop and Spark frameworks in real and virtual cluster configurations can be very useful for the proper scaling-up and efficient job management, especially for machine learning and Deep Learning applications, where Big Data are widely present.

The new adaptive iterative pruning (AIP) approach is proposed. It differs from the standard iterative pruning- retraining scheme by the adaptively changing hyperparameters by linear, multiplicative, or adaptive laws (batch size, number of epochs, a minimal number of channels per layer) that compensate the loss of accuracy due to excessive retraining of the survived weights. It was shown, for example of classification task by VGG-16 model on MNIST dataset, that there is some domain of values where the loss of accuracy could be not higher than 2% with the inference speedup up to $\times 17$ and the loss of accuracy could be not higher than 4% with the inference speedup up to $\times 30$ . In the more general sense, AIP can be widely applied for any deep learning model containing the convolutional layers, i.e. for any convolutional neural networks (CNNs), with the similar speedup of inference time and potentially faster convergence during training.

Purpose: The impact of hybrid quantum-classical neural network (NN) architectures with multiple backbones and quantum transformation as a data augmentation (DA) technique on image classification tasks was investigated using the CIFAR-10 and MedMNIST (DermaMNIST) datasets. These datasets were chosen for their relevance in general-purpose and medical-specific small-scale image classification, respectively. Methods: A series of quanvolutional transformations, utilizing random quantum circuits based on single-qubit rotation quantum gates (Y-axis, X-axis, and combined XY-axis transformations), were applied to create multiple quantum channels (QC) for input augmentation. By integrating these QCs with baseline convolutional NN architectures (LCNet050) and scalable hybrid NN architectures with multiple (n) backbones and separate QC (n) inputs (HNN-QCn), the scalability and performance enhancements offered by quantum-inspired data augmentation were evaluated. The proposed cross-validation workflow ensured reproducibility and systematic performance evaluation of hybrid models by mean and standard deviation values of metrics (such as accuracy and area under the curve (AUC) for the receiver operating characteristic). Results: The results demonstrated consistent performance improvements by AUC and accuracy in HNN-QCn models with the number n (where $n\in \{4,5,9,10,17,18\}$) of backbones and QC inputs across both datasets. The different improvement rates were observed for the smaller increase in AUC and the larger increase in accuracy as input complexity (number of backbones and QCs inputs) increases. It is assumed that the prediction probability distribution is becoming sharpened with the addition of backbones and QC inputs, leading to larger improvements in accuracy. At the same time, AUC reflects these changes more slowly unless the model’s ranking ability improves substantially. Conclusion: The findings highlight the scalability, robustness, and adaptability of HNN-QCn architectures, with superior performance by AUC (micro and macro) and accuracy across diverse datasets and potential for applications in high-stakes domains like medical imaging. These results underscore the utility of quantum transformations as a form of DA, paving the way for further exploration into the scalability and efficiency of hybrid architectures in complex datasets and real-world scenarios.