Model2Vec: Turning Heavy Transformers into Lightning-Fast Lookup Tables
A comprehensive primer on Model2Vec for static embeddings, covering architecture, distillation, PCA, Zipf weighting, and performance.
Machine-Learning
Common docker commands
This post is a tutorial on the commonly used docker commands.
How to choose the probability cut-off in classification problem
This post describes how to choose the probability cut-off in classification problem.
Tutorial on dplyr- a package for data manipulation in R
This post is a tutorial on dplyr - a package for data manipulation in R.
The essence of machine learning is function estimation
This post talks explains how the essence of machine learning is function estimation.
Time series and forecasting using R
This post talks about time series and forecasting.
Diving into H2O with R
This post talks about building machine learning models in H2O using R.
An illustrated introduction to adversarial validation part 2
This post talks about adversarial validation- an approach to the problem of differently distributed training and test data.
An illustrated introduction to adversarial validation part 1
This post talks about adversarial validation- an approach to the problem of differently distributed training and test data.
The curse of bias and variance [draft]
This post talks about the trade-off between bias and variance.