Digests » 29

this week's favorite

Visualizing models 101, using R

That being said, this is a sequel as well as a 101 in and of itself, meaning— like in the last article — that this will be mostly introductory. Go ahead to the end of this article if you want to download the data for yourself and follow along!

Solving NLP task using Sequence2Sequence model: from Zero to Hero

Today I want to solve a very popular NLP task called Named Entity Recognition (NER). In short, NER is a task of extracting Name Entities from a sequence of words (a sentence).

Classification Task Is Hard Without Squashing Function

Why being able to interpret and measure a model’s output is crucial for improving it.

Face detection with NumPy

I have always been fascinated with signal processing, and facial recognition. I wanted to understand signal processing techniques on my own. As a result, I decided to attempt facial detection using only NumPy. I’m not claiming that the following algorithm is the optimal solution. The following guide documents my learning process

Gradient Boosting explained [demonstration]

Gradient boosting (GB) is a machine learning algorithm developed in the late '90s that is still very popular. It produces state-of-the-art results for many commercial (and academic) applications. This page explains how the gradient boosting algorithm works using several interactive visualizations.