Big Data Days 2021
2021-09-28..2021-09-30
-- online --
who it's for
machine learning engineers, data scientists, data engineers, ml project managers, nlp engineers, platform engineers
topics
model distillation and structured pruning; probability calibration trees; data catalog extraction from code; plagiarism detection with Levenshtein; hyperautomation with RPA and CV; oil process prediction with ARIMA and boosting; data labeling and instruction design; neural architecture search for RL agents; natural language data interfaces and intent grammars; metadata folksonomy and slide parsing; Modin pandas parallelization; PostgreSQL and TimescaleDB for IoT storage
| title | author | length |
|---|---|---|
| Training Models | Vadim Strizhov | 49m |
The talk covers methods for training and developing machine learning models, focusing on practical aspects of model upbringing (training, tuning and lifecycle)… | ||
| Probabilistic Calibration Illustrated by Probability Calibration Trees | Valeriy Babushkin | 36m |
Presentation explains probability calibration using Probability Calibration Trees: it addresses the problem of making classifier probability outputs better… | ||
| A Fresh Look at the Data Catalog | Pavel Simanikhin | 44m |
Presentation introduces a new perspective on Data Catalogs: discusses challenges of organizing and discovering data assets and outlines approaches to improve… | ||
| Detecting Plagiarism in News | Aleksey Burnakov | 45m |
A presentation about detecting plagiarism in news articles using Big Data techniques. It covers tools and methods from data science and machine learning to… | ||
| Hyperautomation Through the Eyes of a Software Robot | Sergey Votyakov | 50m |
A software robot-focused talk about hyperautomation: it explains how robotic process automation (RPA) and related automation technologies are used to achieve… | ||
| Predicting Oil Refining Process Quality with Machine Learning | andrey shagalov | 42m |
Presents using machine learning to predict the quality of crude oil processing. Covers employing data-driven models and ML techniques to forecast process… | ||
| Data Quality or Quantity — Which Matters More? | Yuliya Rubtsova | 41m |
A discussion of whether data quality or data quantity matters more for big data and machine learning work. It covers practical trade-offs for Data Science… | ||
| Optimizing a Neural Network Architecture for a Reinforcement Learning Agent | Evgeniy Burnaev | 43m |
The talk discusses optimizing the neural network architecture of an agent that learns via reinforcement learning. It covers techniques for modifying network… | ||
| People-Driven Company vs Data-Driven Company | Aleksey Chernobrovov | 45m |
Compares what changes when companies shift from people-driven to data-driven decision making, naming algorithms and metrics used and whether teams produce… | ||
| NLP or How to Connect Thousands of Users to Data | Yuriy Efarov | 49m |
Presentation explores using NLP to connect thousands of users to data by building natural-language access to datasets and analytics. It covers technologies and… | ||
| Metadata Management Light or How Folksonomy Helps | Anastasiya Viktorova | 33m |
Covers lightweight metadata management using folksonomy: explains how tagging-based, user-driven metadata (folksonomy) can be useful for organizing and… | ||
| Scaling Data Science with Modin | Vasiliy Litvinov | 46m |
Presentation explains how to scale Data Science workflows using Modin, a drop-in accelerated DataFrame library compatible with pandas. It describes using Modin… | ||
| Diagnosing Corporate Culture from Business Communication Lexicon | Marianna Krel, Pavel Poteev | 48m |
Uses analysis of business communication vocabulary to diagnose corporate culture. Describes methods for extracting and measuring lexical features from internal… | ||
| Discovery for API Projects: Where to Start and What to Expect | Kseniya Kalashnikova | 43m |
The talk explains how to run discovery for API-driven projects: where to start, what steps to take, and what outcomes to expect. It covers practical discovery… | ||
| Distributed IoT Telemetry Storage Based on PostgreSQL and TimescaleDB | Ivan Muratov | 52m |
A presentation about building a distributed IoT telemetry storage using PostgreSQL and the TimescaleDB extension. It covers handling IoT telemetry data at… | ||
| Architecture and Implementation of Relational Operators in Distributed SQL Engines | Vladimir Ozerov | 46m |
Covers architecture and implementation of relational operators (like joins, aggregations, filters) inside distributed SQL engines, focusing on how these… | ||
| How to Start Selling a Big Data Product from Scratch: Three Must-Haves | Aleksandr Dmitriev | 37m |
Explains how to start selling a Big Data product from scratch by covering three essential components: product-market fit, go-to-market strategy, and… | ||
| How to Choose an Approach to Managing an ML Project | Askhat Urazbaev | 46m |
Explains how to choose an approach for managing a machine learning project, comparing different project management strategies for ML work. Covers practical… | ||
| Applying Machine Learning Methods to Static Analysis of Executables | elena gerasimova, nikitku organov | 45m |
Describes applying machine learning methods to static analysis of executable files, focusing on using ML techniques to analyze and classify binaries without… | ||
| Neural Networks in Sound Analysis and Generation | Tatyana Zobnina | 44m |
Covers using neural networks for audio analysis and audio generation, discussing architectures and techniques for tasks like sound classification, feature… | ||
| nothing matches | ||