Copy

Newsletter

Hey there, you just received the monthly depends-on-the-definition newsletter for April 2019.

Post of the month: Introduction to embeddings with neural networks
You all might have heard about methods like word2vec for creating dense vector representation of words in an unsupervised way. With this words you would initialize the first layer of a neural net for arbitrary NLP tasks and maybe fine-tune them.
But the use of embeddings goes far beyond that! We can use them to learn supervised representations of arbitrary categorical variables. This makes embeddings a powerful tool for handling categorical data.
Read More

Paper pick

“MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks”, MorphNet takes an existing neural network as input and produces a new neural network that is smaller, faster, and yields better performance tailored to a new problem.

Tips & Tricks

FlashText: Fast search and replace

https://github.com/vi3k6i5/flashtext

Recommended reading

One magical aspect of software is that it just keeps working. If you code a calculator app, it will still correctly add and multiply numbers a month, a year, or 10 years later. This is no longer the case when you are deploying machine learning models. The moment you put a model in production, it starts degrading.

Why Machine Learning Models Crash And Burn In Production
Copyright © 2019 depends-on-the-definition, All rights reserved.