100k YouTube Subscribers
My YouTube channel for applied machine learning tutorials reached 100k subscribers.
Abhishek Thakur
Norway
Abhishek is the World's First Kaggle Quadruple Grandmaster. He has ranked in the top 5 of all four categories on Kaggle. Abhishek's research interests include automated machine learning, hyperparameter optimization, and so on. He is also the author of the applied machine learning book: "Approaching (Almost) Any Machine Learning Problem". In his free time, he likes to make applied machine learning tutorials on his YouTube channel and participate in machine learning competitions. He currently works at Hugging Face where he is building AutoTrain: A no-code tool to train, evaluate and deploy state-of-the-art Machine Learning models automatically. Kaggle: www.kaggle.com/abhishek LinkedIn: www.linkedin.com/in/abhi1thakur Twitter: www.twitter.com/abhi1thakur YouTube: https://www.youtube.com/AbhishekThakurAbhi
Community Contributions
AutoTrain Advanced
Created and maintaining AutoTrain, no code solution to train AI models at Hugging Face.
https://hf.co/autotrain
Diffuzers: web-app and api for 🤗 diffusers
diffuzers is a web ui and deployable API for 🤗 diffusers.
Transfer learning for time series
Transfer learning is a research problem in ML that focuses on storing knowledge gained while solving one problem and applying it to a different but related problem. IT has enabled progress in areas with limited data availability in both CV and NLP domains. Several modern applications of machine learning are built around TL, so it's only natural that people would start thinking about using this approach to time series: while less obvious to formulate (what does it mean to learn time series features across domains), the idea of transfer learning for time series has huge potential. In this notebook we explore the idea in some more detail.
Validation methods for time-series
Every ML practitioner knows that validation matters: while it is common knowledge for classification and regression models, time series models have received less attention on that front. In this episode we will walk through different manners of assessing performance of time series models without breaking the arrow of time.
Data representation for neural networks
In this video, I talk about tensors, ranks, scalers, and vectors, and look at different data types for deep learning.
My First Neural Network using Keras
In this video, we will be building our very first neural network on the MNIST dataset using Keras.
What is deep learning?
This is a video in the Python Deep Learning series which is a book by François Chollet. Deep Learning with Python (2nd Edition, by Francois Chollet). Intro to deep learning.
