?
Compressing deep convolutional neural networks in visual emotion recognition
P. 207–213.
A. G. Rassadin, A. V. Savchenko
In this paper, we consider the problem of insufficient runtime and memory space complexities of deep convolutional neural networks for visual emotion recognition. A survey of recent compression methods and efficient neural networks architectures is provided. We experimentally compare the computational speed and memory consumption during the training and the inference stages of such methods as the weights matrix decomposition, binarization and hashing. It is shown that the most efficient optimization can be achieved with the matrices decomposition and hashing. Finally, we explore the possibility to distill the knowledge from the large neural network, if only large unlabeled sample of facial images is available.
In book
Vol. 1901: Proceedings of the International conference Information Technology and Nanotechnology. Session Image Processing, Geoinformation Technology and Information Security. , CEUR-WS, 2017.
Котов Ф. И., Timokhin I., Ivanov F., , in: 2023 XVIII International Symposium Problems of Redundancy in Information and Control Systems (REDUNDANCY).: IEEE, 2023.
The Successive Cancellation List (SCL) algorithm is a widely used decoding technique in communication systems. However, constructing the critical set for SCL decoding is a challenging task, as it requires a large number of computations and can lead to significant decoding delays. In this paper, a new approach to critical set construction for SCL decoding ...
Added: January 26, 2026
Pikul A. S., Безопасность информационных технологий 2024 Т. 31 № 4 С. 116–127
This article explores the potential use of modern computer vision architectures for the task of deepfake detection. The following architectures are considered: EfficientNet, Vision Transformer (ViT), VisionLSTM (ViL), Vision KAN, and Mamba Vision. The novelty of the approach lies in the application and comparison of these architectures, as well as their combination into paired ensembles ...
Added: December 12, 2025
Seleznev L. E., Chupakhin A. A., Kostenko V. A. et al., Optical Memory and Neural Networks (Information Optics) 2023 Vol. 32 No. 2 P. 73–85
We analyze a classification problem of mentally pronounced Russian phonemes based on data obtained by means of an electroencephalography device. We describe the data collection method as well as the methods of the obtained data processing. To solve the small sample size problem we present the augmentation techniques that use the time stretching and the ...
Added: October 2, 2025
Zabolotniy A., Chan R. W., Moiseeva V. et al., Frontiers in Neuroscience 2025 Vol. 19 Article 1623380
We demonstrated the feasibility of finger movement decoding with a tailored Convolutional Neural Network. The performance of our approach was comparable to complex deep learning architectures, while providing faster and interpretable outcome. This algorithmic strategy holds high potential for the investigation of the mechanisms underlying non-invasive neurophysiological recordings in cognitive neuroscience. ...
Added: October 2, 2025
Cham: Springer, 2025.
This book constitutes the refereed proceedings of 34th International Workshops which were held in conjunction with the 34th International Conference on Artificial Neural Networks and Machine Learning, ICANN 2025, held in Kaunas, Lithuania, September 9–12, 2025.
The 20 full papers and 8 abstracts included in this workshop volume were carefully reviewed and selected from 42 submissions. ...
Added: September 29, 2025
Artem B., Andreasyan A., Konovalov D. et al., Scientific Reports 2025 Vol. 15 Article 23119
G-quadruplexes (GQs) are non-canonical DNA structures encoded by G-flipons with potential roles in gene regulation and chromatin structure. Here, we explore the role of G-flipons in tissue specification. We present a deep learning-based framework for the genome-wide G-flipon predictions across 14 human tissue types. The model was trained using high-confidence experimental maps of GQ-forming sequences ...
Added: August 8, 2025
Shaitan A., Science China Information Sciences 2025 Vol. 68 No. 7 Article 170102
Artificial intelligence (AI) is revolutionizing the field of drug development, particularly in addressing key challenges such as drug response prediction, drug combination design, drug repositioning, and drug molecule generation. Traditional drug discovery is hindered by long timelines, high costs, and low success rates, necessitating innovative technologies to accelerate the process. AI technologies, such as deep ...
Added: June 25, 2025
Boldyrev A., Ratnikov F., Shevelev A., IEEE Access 2025 Vol. 13 P. 102390–102406
The rapid development of machine learning (ML) and artificial intelligence (AI) applications
requires the training of a large numbers of models. This growing demand highlights the importance of
training models without human supervision, while ensuring that their predictions are reliable. In response
to this need, we propose a novel approach for determining model robustness. This approach, supplemented
with a ...
Added: June 15, 2025
Podchufarov A., Galkina A. N., Ванина С. С. et al., Экономика и управление: проблемы, решения 2025 Т. 5 № 4 С. 61–74
Under modern conditions, the introduction of artificial intelligence technologies is becoming a significant factor in the development of high-tech industries. The article presents the results of a study of the prospects for the use of intelligent analytical systems in nuclear energy. The experience of foreign countries is analyzed and the features of successful projects using ...
Added: June 5, 2025
Ryzhova A., Sochenkov I., , in: Proceeding 2019 Ivannikov Ispras Open Conference (ISPRAS).: IEEE Computer Society, 2019. P. 60–67.
Added: May 1, 2025
Walton S., Klyukin V., Artemev M. et al., , in: 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).: IEEE, 2025. P. 3328–3337.
Explicit density learners are becoming an increasingly popular technique for generative models because of their ability to better model probability distributions. They have advantages over Generative Adversarial Networks due to their ability to perform density estimation and having exact latent-variable inference. This has many advantages, including: being able to simply interpolate, calculate sample likelihood, and ...
Added: April 1, 2025
Derkach D., Artemev M., IEEE, 2025.
Added: April 1, 2025
Perelygin V., Kamelin A., Syzrantsev N. et al., Frontiers in Medicine 2025 Vol. 11 Article 1479717
Polygenic risk score (PRS) prediction is widely used to assess the risk of diagnosis and progression of many diseases. Routinely, the weights of individual SNPs are estimated by the linear regression model that assumes independent and linear contribution of each SNP to the phenotype. However, for complex multifactorial diseases such as Alzheimer’s disease, diabetes, cardiovascular ...
Added: March 4, 2025
Ivan Rubachev, Nikolay Kartashev, Gorishniy Y. et al., , in: Proceedings of the 13th International Conference on Learning Representations (ICLR 2025).: ICLR, 2025. P. 53831–53867.
Advances in machine learning research drive progress in real-world applications. To ensure this progress, it is important to understand the potential pitfalls on the way from a novel method's success on academic benchmarks to its practical deployment. In this work, we analyze existing tabular deep learning benchmarks and find two common characteristics of tabular data ...
Added: March 1, 2025
W. Joseph MacInnes, Zhozhikashvili N., Feurra M., , in: First International Conference, AIiH 2024, Swansea, UK, September 4–6, 2024, Proceedings, Part II. Artificial Intelligence in Healthcare. LNCS, volume 14976Vol. 14976.: Springer, 2024. P. 221–234.
Convolutional Neural Networks (CNNs) match human performance in many visual tasks like the classification of images, however they may not simulate the underlying biological processes. We implemented a CNN to try replicate results from an object inversion experiment with Transcranial Magnetic Stimulation (TMS). After training on upright faces, the CNN model went through three stages ...
Added: January 28, 2025
Yury Gorishniy, Ivan Rubachev, Nikolay Kartashev et al., , in: Proceedings of the 12th International Conference on Learning Representations (ICLR 2024).: ICLR, 2024.
Deep learning (DL) models for tabular data problems (e.g. classification, regression) are currently receiving increasingly more attention from researchers. However, despite the recent efforts, the non-DL algorithms based on gradient-boosted decision trees (GBDT) remain a strong go-to solution for these problems. One of the research directions aimed at improving the position of tabular DL involves ...
Added: January 22, 2025
Boldyrev A., Derkach D., Ratnikov F. et al., EPJ Web of Conferences 2024 Vol. 295 Article 09008
Calorimeters are a crucial component for most detectors mounted on modern colliders. Their tasks include identifying and measuring the energy of photons and neutral hadrons, recording energetic hadronic jets, and contributing to the identification of electrons, muons, and charged hadrons. To fulfill these many tasks while keeping costs reasonable, the calorimeter construction requires good and ...
Added: January 8, 2025
Morozov D., Garipov T., Lyashevskaya O. et al., Journal of Language and Education 2024 Vol. 10 No. 4 P. 71–84
Introduction: Numerous algorithms have been proposed for the task of automatic morpheme segmentation of Russian words. Due to the differences in task formulation and datasets utilized, comparing the quality of these algorithms is challenging. It is unclear whether the errors in the models are due to the ineffectiveness of algorithms themselves or to errors and inconsistencies ...
Added: January 7, 2025
Gorishniy Y., Kotelnikov A., Babenko A., , in: The Thirteenth International Conference on Learning Representations: ICLR 2025.: ICLR, 2025.
Deep learning architectures for supervised learning on tabular data range from simple multilayer perceptrons (MLP) to sophisticated Transformers and retrieval-augmented methods. This study highlights a major, yet so far overlooked opportunity for substantially improving tabular MLPs: namely, parameter-efficient ensembling -- a paradigm for implementing an ensemble of models as one model producing multiple predictions. We ...
Added: December 24, 2024