About Luciano Strika

Luciano Strika is a computer science student at Buenos Aires University, and a data scientist at MercadoLibre. He also writes about machine learning and data on www.datastuff.tech.

Luciano Strika Posts (7)

• Convolutional Neural Networks: A Python Tutorial Using TensorFlow and Keras - 26 Jul 2019
  
  Different neural network architectures excel in different tasks. This particular article focuses on crafting convolutional neural networks in Python using TensorFlow and Keras.
• Training a Neural Network to Write Like Lovecraft - 11 Jul 2019
  
  In this post, the author attempts to train a neural network to generate Lovecraft-esque prose, known to be awkward and irregular at best. Did it end in success? If not, any suggestions on how it might have? Read on to find out.
• 5 Probability Distributions Every Data Scientist Should Know - 04 Jul 2019
  
  Having an understanding of probability distributions should be a priority for data scientists. Make sure you know what you should by reviewing this post on the subject.
• 3 Machine Learning Books that Helped me Level Up as a Data Scientist - 28 May 2019
  
  Each of these books has helped me immensely in different stages of my career as a Data Scientist, particularly in my role as a Machine Learning Engineer.
• Autoencoders: Deep Learning with TensorFlow’s Eager Execution - 20 May 2019
  
  Deep Learning has revolutionized the Machine Learning scene in the last years. Can we apply it to image compression? How well can a Deep Learning algorithm reconstruct pictures of kittens? What’s an autoencoder?
• Intro to XGBoost: Predicting Life Expectancy with Supervised Learning - 08 May 2019
  
  Today we’ll use XGBoost Boosted Trees for regression over the official Human Development Index dataset. XGBoost is a framework that allows us to train Boosted Trees exploiting multicore parallelism.
• K-Means Clustering: Unsupervised Learning for Recommender Systems - 16 Apr 2019
  
  In this article we apply unsupervised learning on a Magic: The Gathering dataset in order to build a system for making recommendations.