A Transformer-Based Framework for Multivariate Time Series Representation Learning
Offered By: Launchpad via YouTube
Course Description
Overview
Explore a cutting-edge Transformer-based framework for multivariate time series representation learning in this 21-minute Launchpad video. Gain insights into the challenges data scientists face with time series analysis, understand the power of Transformers in addressing these issues, and discover the TST Base Model. Learn about unsupervised pre-training and supervised fine-tuning techniques, and delve into practical applications such as classification and data imputation/forecasting. Evaluate the framework's effectiveness and expand your knowledge of advanced time series analysis methods.
Syllabus
Intro
I've never worked with Time Series data
What do data scientist think of time series analysis
Technical Challenges with Time Series
Transformers is all we need
TST Base Model
Unsupervised Pre-training
Supervised fine-tuning
Classification
Data Imputation/forecasting
How well does it work?
Taught by
Launchpad
Related Courses
Big Self-Supervised Models Are Strong Semi-Supervised LearnersYannic Kilcher via YouTube Inside ChatGPT- Unveiling the Training Process of OpenAI's Language Model
Krish Naik via YouTube Fine Tune GPT-3.5 Turbo
Data Science Dojo via YouTube Yi 34B: The Rise of Powerful Mid-Sized Models - Base, 200k, and Chat
Sam Witteveen via YouTube LLaMA 2 and Meta AI Projects - Interview with Thomas Scialom
Aleksa Gordić - The AI Epiphany via YouTube