The world’s leading publication for data science, AI, and ML professionals.

Weekly Selection – May 24, 2019

The Quiet Semi-Supervised Revolution

By Vincent Vanhoucke – 5 min read

One of the most familiar settings for a machine learning engineer is having access to a lot of data, but modest resources to annotate it.


How I Went from a Journalist to a Data Scientist

By Yao Yang – 5 min read

Where shall I start? I guess I’ll start with the most recent. I am currently a research data scientist at Accenture AI Labs, we do ML research and we prototype them.


Lagrange multipliers with pictures and code

By Rohit Pandey – 16 min read

In this story, we’re going to take an aerial tour of optimization with Lagrange multipliers. When do we need them? Whenever we have an optimization problem with constraints.


Parsing Structured Documents with Custom Entity Extraction

By Dale Markowitz – 6 min read

Entity Extraction (EE) is also useful for parsing structured documents like forms, W4s, receipts, business cards, and restaurant menus (which is what we’ll be using it for today).


Precision and Recall Trade-off and Multiple Hypothesis Testing

By Giacomo Vianello – 17 min read

In my previous job as an Astrophysicist, I was working on detecting explosions of large stars (GRBs) releasing an incredible amount of energy.


LSTM Autoencoder for Extreme Rare Event Classification in Keras

By Chitta Ranjan – 13 min read

Here we will learn the details of data preparation for LSTM models, and build an LSTM Autoencoder for rare-event classification.


Optimization with Python: How to make the most amount of money with the least amount of risk?

By Tirthajyoti Sarkar – 7 min read

We show how to apply a Nobel-prize winning economic theory to the stock market and solve the resulting optimization problem using simple Python programming.


The Hitchhiker’s Guide to Feature Extraction

By Rahul Agarwal – 13 min read

Good Features are the backbone of any machine learning model. And good feature creation often needs domain knowledge, creativity, and lots of time.


The Simpsons meets Data Visualization

By Adam Reevesman – 9 min read

There are few things I love more than ​The Simpsons​. It is one of those shows that I think about on a daily basis. With thirty seasons and over 600 episodes, the animated comedy show holds a special place in my heart.


Predicting the Popularity of Instagram Posts

By Guilherme Regos Zamorano – 16 min read

Using a mixed input neural network to achieve great predictions for Instagram popularity.


Related Articles