Sciblog - A blog designed like a scientific paper

 

D4 Data Podcast with Miguel Fierro - Recommendation Systems

Oct. 1, 2022

Deepak JR and Miguel González-Fierro

 
 

Deepak JR interviewed me for his podcast D4 Data Podcast where we discussed everything about recommendation systems. Recommendation systems are one of the most impactful machine learning systems in production in the world. It is not a surprise that they are one of the most complex and demanding solutions, with multiple moving parts that need to be tuned in the right way to improve the user experience and increase revenue.

 
 

An Analysis of the Adoption of Top Deep Learning Frameworks

July 27, 2022

Miguel González-Fierro

 
 

There are a lot of people comparing deep learning frameworks in terms of speed or performance, but I haven't seen anyone studying their adoption over time and analyzing the underlying reasons why some attracted more users than others. In this post, I share what I have observed since 2015, and based on historical data, I provide guidance on one of the top questions I get: what deep learning framework should I use?

 
 

My most popular LinkedIn posts of 2021

Feb. 26, 2022

Miguel González-Fierro

 
 

In 2021, I started posting on LinkedIn more consistently. A lot of my posts are about simplifying AI concepts so people can discover the field, learn something new or even grow their career in Data Science. In 2021 I got around 2 million views in my content, here are some of the most popular posts.

 
 

A Gentle Introduction to Distributed Training with DeepSpeed

Jan. 30, 2022

Miguel González-Fierro

 
 

DeepSpeed is an open-source library that facilitates the training of large deep learning models based on PyTorch. With minimal code changes, a developer can train a model on a single GPU machine, a single machine with multiple GPUs, or on multiple machines in a distributed fashion. In this post, we review DeepSpeed and explain how to get started.

 
 
 
 

Matrix Factorization is one of the most widely used methods in Recommendation Systems, whose ultimate goal is to understand what is the user preference for a set of items. For example, Netflix tries to understand what movie you would like to watch next. In this post, we explain in simple terms how Matrix Factorization works.