lucasmoura’s blog

Another variable in the Deep Learning hyperspace

  • Funk Generator

    This post describes a language model that I have created for generating funk lyrics. This is a popular music genre in Brazil, I have created a medium post in portuguese describing the process of collecting the data and generating the songs. Therefore, my motivation in this posts is to explain how I created this model and discuss some decisions I have made during the development of this project. Word Embeddings I have not used any portuguese pre-trained word embedding for this problem.

    Read more…
  • Automatic Star Rating for Movie Reviews Part 3

    In the previous part of this series, I created a Bag Of Words model to classify the reviews. In this part, I will present two other models I have implemented, a Recurrent and Convolutional model. Data Preprocessing The data pre-processing used in the previous part of this series was applying tokenization to the movie reviews, removing the common Portuguese stop words and turning each token into a word-id that references a row in the word embedding matrix (This row represents the original token).

    Read more…
  • Automatic Star Rating for Movie Reviews Part 2

    In the previous part of this series, I presented the Dataset of movie reviews I gathered and analyzed it a little. Now it is time to train a model using it. The first model I tried is a Bag Of Words model, as can be seen in the following picture. In the above image, we can see that the model receives an array of word-ids. An id represents a unique word that can be found in a movie review.

    Read more…
  • Automatic Star Rating for Movie Reviews - Part 1

    One of my favorite hobbies in the world is watching movies. Usually, if I stay one week without watching a new film I feel that something is wrong. After watching a movie, I read reviews from different critics on the Internet, to look into different opinions about the movie I just saw or just to learn something new about movies in general. Most of the critics that I read rate their movies using the “star” rating, where a film gets a rate ranging from one to five stars.

    Read more…
  • AppRecommender Gsoc Final Report

    With Google Summer of Code 2016 coming to an end, it is time to write my final report about it. This was an amazing experience to have. Not only on the technical side, but it has allowed me to meet and interact with awesome people, which helped to improve a lot not only my coding skills, but the way I was interacting with other people inside the community. Debian Working with Debian was also another high point of the my Google Summer of Code experience.

    Read more…
  • AppRecommender My Google Summer of Code Project

    AppRecommender is a package recommender system for Debian. This project is also one of the Debian projects that is being worked on by some Google Summer of Code students. As one of these students, I will now present what my Google Summer of Code project is and what I have achieved so far. First of all, my project is to allow AppStream to parse recommendations provided by AppRecommender. AppStream is a project that aims at providing cross-distribution metadata about components that can be installed by an user.

    Read more…
  • AppRecommender a Package Recommender System

    Hello, my name is Lucas Moura and this post will present AppRecommender. This project is a package recommender system for Debian systems. The intent of this application is to look for packages that users have already installed in their system and recommend new useful packages based on them. This approach is similar as the one seen on Netflix or Amazon, where the movies or goods that a user has already seen determine other items that will be recommended.

    Read more…