Sciblog - A blog designed like a scientific paper

 

My Most Popular LinkedIn Posts Of 2022

Jan. 2, 2023

Miguel González-Fierro

 
 

In 2022 around 11 million people saw my posts on LinkedIn. I've been posting to help people understand and apply AI. In particular, I focused on how people can switch their careers to AI because that's the journey I followed. Here are some of the most popular posts.

 
 

Building Recommender Systems

Nov. 26, 2022

Seth Juarez and Miguel González-Fierro

 
 

Recommendation systems are one of the most exciting AI solutions available today. They are information filters that learn users' behavior based on their historical interactions with items, and then predict their preferences for a given item. In this post, we make an overview of Recommenders, the open-source repository that helps Data Scientists build recommendation systems.

 
 
 
 

Whether you are interested in changing your career to an AI position or you want to improve your skills as a Data Scientist, it is key to know how to effectively create machine learning projects. In this post, I show how to start a machine learning project, by combining two of the most useful tools we have at our disposal, Jupyter notebooks and Python libraries. See the full video to discover how I create projects in my job at Microsoft.

 
 

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?