Every day, sales managers in Tochka call to 3000+ customers, but what if we can influence this process and select customers to call for each seller? I'll tell you how we made a machine that ranks companies by the likelihood of converting into a client, and then converted it into a kind of Tinder: cards with contacts are divided between sellers every day based on personal speeds, predicted productivity and urgency of the call. I will touch on the technical side of the personal speed prediction machine + card booking strategy and how to choose the optimal booking time window. I'll also show you how much money we made from this.

Exploitation of neural network on scaling and subsequent optimization of brand advertising campaigns, with the condition of increasing the share of targeted bids and without cannibalization of organic traffic

During my lecture, I'll explain how we at Kontur.Focus developed and integrated a dynamic model for assessing the probability of bankruptcy into our product. This model is designed to help Kontur.Focus users in assessing the reliability of counterparties, as it has a predictive ability to assess the risk of bankruptcy of a company based on financial statements, arbitration claims and other events. We will analyze the details of training and deploying the model, what difficulties we encountered during integration, and how we collected feedback on the new feature.

The development of large language models and speech synthesis systems has led to the emergence of "intelligent" agents in virtual worlds. These agents also require correct gestures during interaction with humans. In this talk I will tell you how these gestures can be generated from speech and more. Here I present our approaches for conversational gestures generation emerged from participation in the GENEA Challenges, which led us to three papers. I will describe the problem itself, the first models for solving it and our approaches. What the main limitation of autoregressive models that we encountered, how we tried to overcome it and how video games helped us.

In the realm of Over-The-Top (OTT) and Video On Demand (VOD) services, two principal challenges significantly impact operational efficiency: churn rate and content utilization. A high churn rate undermines the efforts invested in user acquisition, while suboptimal content utilization can decrease viewer interest, further exacerbating the churn issue. These platforms often allocate the largest portion of their budgets to acquiring new users and securing content rights. Therefore, addressing the critical questions of how to maintain viewer engagement and which content to acquire—or how to better leverage existing content—becomes essential for success in the OTT/VOD industry.
A study by PWC highlights that viewer retention correlates positively with the breadth of content consumed, indicating that a diverse and engaging content library is key to reducing churn rates. Given this, market leaders heavily invest in sophisticated recommendation algorithms, seeking to differentiate themselves in a highly competitive market.
The upcoming conference presentation will explore strategies for companies that may not have the resources to compete directly with industry giants. It will delve into how these organizations can still access cutting-edge technology in recommendation systems to enhance viewer engagement and make informed content acquisition decisions, thereby finding their own path to success in the crowded OTT/VOD marketplace.

The topic is probabilistic programming and generative probabilistic models. Probabilistic programming allows incorporating expert knowledge and assumptions into machine learning models, primarily about the interrelationships of various factors, and taking into account unobservable factors that control the process of data generation. As a practical example, let us consider the task of determining the latent needs that determine the structure of customers' receipts.

A.N. Kolmogorov is the greatest mathematician of the 20th century, the founder of modern probability theory, who also laid the foundations for the theory of Markov random processes with continuous time. These results, which had a huge impact on the development of applied methods of signal processing, filtering, modeling and financial data processing, have again come into the spotlight in the 21st century due to the development of artificial intelligence and its applications. Indeed, to solve such important applied problems as increasing the resolution of images, synthesizing speech from text, generating images based on text descriptions, etc., effective generative modeling methods are required that are capable of generating objects from a distribution specified by a sample of examples. Recent advances in the field of generative modeling are precisely based on diffusion models and use the mathematical foundation laid in the last century by A.N. Kolmogorov and his followers. The report will talk about modern approaches to generative modeling based on diffusion processes and based on solving the Monge-Kantorovich problem. The connection between the solution of the entropy-regularized Monge-Kantorovich problem and the problem of constructing a diffusion process with certain extremal properties will be shown. The operation of the corresponding algorithms will be demonstrated using the example of solving various image processing problems.

Modern neural networks are an extremely resource-intensive algorithms in terms of memory, computation, and energy. This results in additional costs for their use and also limits their use on Edge devices. The report discusses the problems of inferring neural networks from a hardware and software point of view. In the first, we briefly discuss the von Neumann bottleneck problem and how to bypass it. In the second, we discuss the main neural netowrk optimization approaches such as: pruning, quantization, distillation, their variants and their combinations. At the same time, we will compare modern AI systems with the brain and explain the reasons for the greater efficiency of the brain. We will show that the most effective approaches to optimizing AI systems use (in some sense) brain-based principles.

undefined

We will show you how we use and improve transformers and which kind of algorithms we use to generate synthetic data to predict rare defects on conveyor belts

1. Who are the mathematicians in the MMK? 2. What kind of problems they are solving by using different methods and instruments? 3. What is the economic effect of the application of the mathematical modelling? 4. Why mathematical modelling is related to the machine learning? 5. What kind of the case studies we have already carried out?

We will talk about the ability of Large Language Models (LLMs) to provide personalized business-oriented communication with the help of agents. We also tackle the problem of finetuning and adding new modalities for practical applications. Finally, we formulate core challenges and approaches for building applications over LLMs.

We propose a novel, multi-agent approach to solving mathematical reasoning problems. LLMs have shown significant progress in solving math problems, but they have fundamental limitations and do not achieve high quality solutions consistently. In the proposed approach, agents self-organise to create a strategy for solving the problem on the fly, thus achieving robust solutions to a whole class of mathematical arithmetic reasoning tasks.

A new neuro-symbolic architecture of large language models is presented. It combines unsupervised learning and reinforcement learning and requires several orders of magnitude less computing for learning compared to neural network language models. The complexity of learning in the proposed architecture increases linearly with the size of the data, in contrast to the quadratic dependence in neural network models of the language.

We explore predicting startup success using CrunchBase data and deep learning. Our model forecasts milestones like IPOs, unicorn status, and M&A for Series B and C startups. We achieved 14x capital growth (98th percentile of VC funds), identified high-potential startups, and stress the importance of diverse data for accuracy. This work shows deep learning's promise in startup success prediction.

Neovascular age-related macular degeneration (n-AMD) is a form of AMD that is responsible for most cases of severe vision loss. Anti-VEGF therapy, which is the gold standard for the treatment of this pathology, is accompanied by OCT monitoring. However, this process is hampered by the lack of methods for accurately quantifying OCT images. The aim of this study is to develop and evaluate the accuracy of the automated calculation of the quantitative characteristics of PED, SRF and IRF biomarkers. The study material included OCT B-scans of patients with n-AMD and pigment epithelial detachment who underwent anti-VEGF therapy from 2014 to 2021. OCT B-scans obtained from a CirrusHD-OCT 5000 Carl Zeiss Meditech device. The neural network for OCT image segmentation was trained on a dataset including 251 and 385 images from Experiments 1 and 2, respectively. The images were annotated by experts highlighting PED, SRF and IRF biomarkers using Labelme software. Data preprocessing included image resizing, normalization, and conversion to grayscale format. The data set was divided into training and validation. To segment retinal structures, the UNET architecture with the Adam optimizer and the Categorical Cross-Entropy loss function was used. The algorithm for calculating quantitative biomarker characteristics was based on edge detection using the method of Satoshi Suzuki and KeiichiA be. Testing data set for access the efficiency of system that included algorithms for segmentation and calculation of quantitative characteristics of biomarkers, included 241 images for which the length and height of the PED were measured by a physician using built-in software. Also, the image data were marked with respect to 3 anatomical treatment outcomes: attached PED; non-attached PED; PED tear. The developed method for processing OCT images made it possible to segment the biomarkers PED, SRF and IRF with high accuracy. The segmentation model shows the best results for PED (0.9), but also shows good accuracy for SRF and IRF (0.72 and 0.69) with increasing number of training data in experiment 2. Automated algorithm for calculating quantitative characteristics of biomarkers on the test set data from patients with n-AMD showed no statistically significant difference when comparing measurements with a physician. The study also showed that the attached and non-attached PED groups were statistically significantly different regarding the height, extent and area of the PED. In addition, IRF area may also be a predictor of PED tear, since its values are statistically significantly different for groups 2 and 3. Thus, automated segmentation and calculation of biomarkers can achieve performance comparable to an ophthalmologist in assessing the quantitative characteristics of biomarkers in cases of neovascular macular degeneration.

The main part of the presentation will address the problem of effective planning of radiation therapy. For planning, it is necessary to segment a large number of anatomical structures. The task of segmentation is complicated by the fact that 1) three-dimensional medical images are used and 2) the organs of patients are abnormal. For these reasons, the results of automatic segmentation require manual corrections. An approach will be presented to optimize the segmentation correction process in real time based on information about the doctor's view. In the additional part of the presentation, the problem of interpretability of deep models will be considered.

Radiologists dedicate more than half of their diagnostic time to in- terpreting computed tomography (CT) scans, with chest and abdominal scans being particularly detailed and time-intensive due to the need to meticulously identify and describe a variety of diseases. Our cutting-edge product simultaneously analyzes 10 different diseases in these scans, in- cluding disorders affecting the lungs, heart, bones, and abdominal regions. In this study, we demonstrate how introducing an AI-assisted study pro- vides a substantial time-saving advantage and lessens the heavy workload currently borne by radiologists. Specifically, it saves up to 20% of the time spent on CT examinations (≈ 2.5 mins on average), and increases the average recall by over 29%, while preserving the same level of positive predictive value.

In this talk we will describe the challenges congestion control for file transfer has, propose an implementation of congestion control algorithm based on Reinforcement Learning techniques and show how it was applied in real life

Over the past years, foundation models and LLMs have demonstrated enhancements in measurable aspects and the development of new qualitative features, creating a need for their comprehensive evaluation and analysis of the associated risks. To address these issues, we present MERA, a new instruction benchmark for evaluating foundation models oriented toward the Russian language. The benchmark encompasses 21 evaluation tasks for generative models. The talk presents the new evaluation methodology, an open-source code base for the MERA assessment, a leaderboard with a submission system, and the evaluated baselines' results.

This presentation aims to provide a comprehensive overview of Federated Learning, highlighting its recent developments, applications, and trends as of 2023. Federated Learning, a rapidly evolving field in machine learning, involves training algorithms across decentralized devices or servers while keeping data localized. The talk will commence with a brief introduction to Federated Learning, elucidating its core principles and significance.

Following this, the presentation will delve into various key cases and application areas, demonstrating the practical utility and versatility of Federated Learning in diverse sectors. A significant portion of the talk will be dedicated to discussing the advancements in this domain over the course of 2023. This examination is grounded in a thorough study of the general informational landscape on this topic, encompassing an analysis of thematic conferences, academic publications, updates to open-source tools, and GitHub repositories.

Additionally, the presentation will showcase a curated collection of news from companies developing solutions in this area, aiming to provide insights into the business and technological implications of these developments. A critical evaluation of the maturity level of Federated Learning technology will be offered, assessing its readiness for widespread adoption. This assessment will touch upon the challenges faced, potential risks, and the future prospects of Federated Learning, providing a well-rounded perspective on its current state and future trajectory.

Node2Vec is a widely used algorithm for learning feature representations of the graph nodes. This algorithm is intensivelly used in multiple highload applications. Thus its performance is very important. There are two reference implementations of the Node2Vec in C++ and Python from Stanford Network Analysis Project (SNAP). However, their performance is not optimal. We introduce an optimized implementation of the Node2Vec algorithm, which performance is 2.5-5.1 times higher than the reference ones. We also prove that the accuracy of the optimized algorithm stays the same by solving a multi-label node classification problem on several datasets.

Linguistic and logical text structures are very useful for some applied tasks like dialogue generation, argument mining and fact verification. We will consider several cases of such tasks: multi-party dialogue generation by means of discourse structure and also fact correction based on information retrieval combined with logical reasoning.

Robust Reinforcement Learning (RRL) is a promising Reinforcement Learning (RL) paradigm aimed at training robust to uncertainty or disturbances models, making them more efficient for real-world applications. Following this paradigm, uncertainty or disturbances are interpreted as actions of a second adversarial agent, and thus, the problem is reduced to seeking the agents' policies robust to any opponent's actions. This paper is the first to propose considering the RRL problems within the positional differential game theory, which helps us to obtain theoretically justified intuition to develop a centralized Q-learning approach. Namely, we prove that under Isaacs's condition (sufficiently general for real-world dynamical systems), the same Q-function can be utilized as an approximate solution of both minimax and maximin Bellman equations, and we also indicate conditions when this Q-function can be decomposed. Based on these results, we present the Isaacs Deep Q-Networks (IDQN) and Decomposed Isaacs Deep Q-Networks (DIDQN) algorithms, respectively. We analyze their performance by comparing them with other baseline RRL and Multi-Agent RL algorithms. We consider both simple environments with known accurate solutions and complex large-dimensional MuJoCo environments. In each experiment, we thoroughly evaluate the agents' policies obtained after learning, training opponents against them using various RL algorithms with various parameters. The experiment results demonstrate the superiority of the presented algorithms in all experiments under consideration.

As industry needs to process growing amounts of training data, reduce the cost of fine-tuning a single model, and minimize the environmental effects, the task of accelerating the fine-tuning of large language models (LLM) has become extremely demanding. DAREL is a novel training data reduction method that operates with training samples based on losses obtained from a currently trained model or a pre-trained one. The proposed method is devoted to Large Language Models fine-tuning and is designed primarily to be combined with Parameter-Efficient fine-tuning methods, such as LoRA. The results of computational experiments provide compelling evidence of the enhancement of the fine-tuning quality and time of Large Language Models. DAREL allows an average 1.26x fine-tuning acceleration for GPT2-S, GPT2-M and GPT2-L on a variety of datasets, including E2E-NLG, DART and WebNLG, with an average BLEU drop of 1.44 p.p.

Automatic humor detection is a highly relevant task for conversational AI. To date, there are several English datasets for this task, but little research on how models trained on them generalize and behave in the wild. To fill this gap, we carefully analyze existing datasets, train RoBERTa-based and Naïve Bayes classifiers on each of them, and test on the rest. Training and testing on the same dataset yields good results, but the transferability of the models varies widely. Models trained on datasets with jokes from different sources show better transferability, while the amount of training data has a smaller impact. The behavior of the models on out-of-domain data is unstable, suggesting that some of the models overfit, while others learn non-specific humor characteristics. An adversarial attack shows that models trained on pun datasets are less robust. We also evaluate the sense of humor of the chatGPT and Flan-UL2 models in a zero-shot scenario. The LLMs demonstrate competitive results on humor datasets and a more stable behavior on out-of-domain data. We believe that the obtained results will facilitate the development of new datasets and evaluation methodologies in the field of computational humor. We've made all the data from the study and the trained models publicly available.

Reinforcement Learning is used for solving of different problems and tasks in different subject areas (traffic control, behavior modelling, SW testing, cybersecurity etc.). There are a lot of real-world tasks when a single agent have to cope with other agents (to coordinate or compete) and multi-agent systems (MAS) is used for such situations. High-dimensional RL-MAS environment causes "curse of dimension" problem and deep learning helps to solve this problem efficiently. This presentation covers some examples of using RL and DeepRL for multi-agent systems.

We will discuss why we decided to combine multimodal networks, unlabelled data, and a fresh perspective on the DICOM format into a single fundamental model. We'll explore what this has brought us and why the future lies in this direction.

Diffusion models became state-of-the-art tool for generative modelling. However they remain underexplored and the reasons for their success are not fully understood yet. In the talk we will consider them from different perspectives and discuss how basic model can be extended based on those perspectives. In particular we will try to understand what elements of diffusion model are crucially important and what can be omitted without loss in quality.

Spiking Neural Networks (SNNs) implemented on neuromorphic processors is one of the promising approaches to creating energy-efficient, high-performance, and autonomously adaptive Edge AI. The development of such systems is influenced by the binary and event-driven nature of data in SNNs and the "near-memory computing" principle implemented in neuromorphic processors. This talk explores methods and key implementation features of SNNs on the neuromorphic chip "AltAI" using the Kaspersky Neuromorphic Platform. An interesting aspect of hardware-oriented SNN topologies, such as resilience to common AI attack methods, is discussed. As a proof-of-concept, a neuromorphic detector for adversarial attacks on a facial biometric identification system is presented.

The report will provide an overview of current trends in the direction of neuromorphic artificial intelligence systems. In terms of neuromorphic properties (connectionism, parallelism, asynchrony, pulsed nature of information transfer, on-device learning, local learning, sparsity, analog computing and in-memory computing), the most striking projects in the world will be considered. Particular attention will be paid to new products of the last year - IBM NorthPole, the second generation of Akida, chips based on memristive computing.

Calculate metrics on a test dataset, test API performance - is this enough to ensure reliable operation of medical CV systems in production? Obviously not, especially for offline work scenarios. So in this report I will tell you about the most dangerous and frequent errors in the testing process that we have encountered in 5 years of development

We will talk about the ML approaches we have used to anonymize the personal data of a 15 tb database of a large medical company, which will allow us to train new algorithms in the diagnosis and treatment of diseases.
Since medicine is the most difficult case in the field of anonymization and contains 3 times more heterogeneous unstructured data, complex PD patterns. Our methods may be of interest to a large number of participants in various industries such as banks, retail and telecom.

Spiking neural networks (SNN) and non-von-Neumann massively parallel computers are considered as a theoretical and hardware basis for creation of so-called neuromorphic intelligent systems, which are more similar to human brain functioning than traditional artificial neural networks (ANN) based on deep learning. First of all, instead of the biologically implausible error backpropagation algorithm, SNN learning is based on the local synaptic plasticity rules stipulating that synaptic connection strength dynamics only depend on activity and properties of the neurons connected. The local learning algorithms are possible in completely asynchronous SNNs – when the SNN is a huge ensemble of independent simple computational units. This feature and the explicit inclusion of the temporal dimension in the SNN functioning in the form of neuron state dynamics and non-zero spike propagation time explain the growing attention to SNNs from the viewpoint of reinforcement learning (RL) tasks – because this learning regime requires continuous learning and should work under conditions of significant time gaps between network decisions and their evaluations. In this presentation, the SNN structures, neuron and synaptic plasticity models used for RL are considered. The specific SNN-based mechanisms of the model-free and model-based RL are analyzed. The efficiency of implementation of the SNNs used for RL on modern and future neuroprocessors is estimated.

The emergence of generative AI, improved quality of 3D rendering and modeling significantly expand the use of synthetic data for training ML models. In the overview report, I will tell you how things are at the beginning of 2024: - which methods prevail in the market - pros/cons of each method - examples of generations - assessment of the prospects of methods

In this talk, we introduce HypoFinder, an innovative tool utilizing a state-of-the-art Large Language Model to fundamentally enhance the initial phases of scientific inquiry. We will showcase HypoFinder's robust capabilities, starting with its automated formalism selection, vital for crafting solid hypotheses. Our exploration extends to the tool's ability to compose meticulous research plans informed through the meticulous analysis of a curated body of scholarly articles. We will spotlight HypoFinder's powerful background search function, which automates the extraction and summarization of information from relevant papers, thus equipping researchers with concise, essential knowledge of their field's current and foundational works. The talk will provide insight into the LLM technology propelling HypoFinder, with demonstration cases including the search for new solid ion electrolyte materials—pivotal in battery technology—and the formulation of a winning strategy for pinewood derby, showcasing HypoFinder's versatility across diverse research scenarios. We will discuss practical implementations, reflecting on how automation like HypoFinder could remodel scientific creativity, efficiency, and collaboration, reshaping the future of scientific endeavors.

Generative AI is one of the cutting-edge areas in machine learning. It is primarily associated with images and have gained worldwide popularity thanks to networks for image creation: Dall-E, Stable Diffusion, and Midjourney. But in this talk we will not talk about images. Generative models have also been widely used in natural sciences and industrial applications. We will consider several cases in astronomy and high-energy physics experiments at the Large Hadron Collider. Finally, we will discuss how generative models are used to model the behavior of complex systems and data anonimization.

I'll tell you how we combat hallucinations and data obsolescence in GigaChat using the RAG (Retrieval-Augmented Generation) approach