Plurrrr

a tumblelog
Fri 26 Jun 2020

Chromatopelma cyaneopubescens eating

In the afternoon I gave the Chromatopelma cyaneopubescens, common name "Green Bottle Blue" (GBB for short), that I keep a mealworm.

Chromatopelma cyaneopubescens eating
Chromatopelma cyaneopubescens eating.

This tarantula molted a week ago.

Logistic Regression from scratch

Sometimes it's necessary to split existing data into several classes in order to predict new, unseen data. This problem is called classification and one of the algorithms which can be used to learn those classes from data is called Logistic Regression.

Source: Logistic Regression from scratch, an article by Philipp Muens.

PyTorch - how it is designed and why

Pytorch is a pretty intuitive tensor library which can be used for creating neural networks. There are many features in the framework, and core ideas that should be understood before one can use the library effectively.

The original tutorial by pytorch provides a very good introduction that guides the users along different concepts, explaining the different abstraction used in the framework. It was a pretty involved read, and assumes some knowledge on neural networks before everything on the page makes sense. So here, we will be filling in some of these gaps.

Source: PyTorch - how it is designed and why, an article by Ong Shu Peng.

Deciphering Python's Metaclasses

In Python, metaclass is one of the few tools that enables you to inject metaprogramming capabilities into your code. The term metaprogramming refers to the potential for a program to manipulate itself in a self referential manner. However, messing with metaclasses is often considered an arcane art that’s beyond the grasp of the proletariats.

Source: Deciphering Python’s Metaclasses, an article by Redowan Delowar.