Month: February 2022

The recommended articles the author has read this week.
This letter is posted every Monday.

This week, the articles about VAE(Variational Autoencoder) are introduced.

Pyro tutorial: Variational Autoencoders

A tutorial of VAE by Pyro, which is a universal probabilistic programming language (PPL) written in Python and supported by PyTorch on the backend. 

Variational Autoencoder: Intuition and Implementation

The theoretical background of VAE is written in detail.

The author also introduces several new features in the following articles.

The recommended articles the author has read this week.
This letter is posted every Monday.

Include diagrams in your Markdown files with Mermaid

An informative GitHub blog about how to create diagrams in markdown.

Practical Quantization in PyTorch

The PyTorch official blog about a quantization method. Quantization is a method for making your DNN run faster and with lower memory.

The author also introduces several new features in the following articles.

The recommended articles the author has read this week.
This letter is posted every Monday.

Comparison of AutoML solutions 2021

AutoML is one of the hot topics. Recently, however, there are many AutoML tools. In this article, we can check the recent trend.

Run Your Python Code as Quickly as C++

We sometimes face the problem that our python code is NOT as fast as we expect. This article introduces a really simple method to fast our python code.

The author also introduces several new features in the following articles.

The recommended articles the author has read this week.
This letter is posted every Monday.

T-distributed Stochastic Neighbor Embedding(t-SNE)

The techniques to reduce the dimensionality of a dataset are important because we can understand a dataset visually. Principal component analysis(PCA) is known as one of the most famous techniques. However, t-SNE is also might be a good choice because this technique can reflect the nonlinearity than that of PCA.

What makes LightGBM lightning fast?

LightGBM, one of the decision-tree-method libraries, is known as the faster library. This article demonstrates features of how to facilitate computational speed.

The author also introduces several new features in the following articles.