NATURAL LANGUAGE PROCESSING
Spanish Language model
122000+ wikipedia spanish articles to create a language model (next word prediction). Technologies involved: Python (Fastai2).
Emotions in tweets
Tweets classification into 13 different emotions using two different models: one using a random forest and other using a Long Short Term Memory (LSTM) neural network.
Technologies involved: Python (Nltk, Tensorflow-Keras).
Sentiment analysis for movie reviews
Classification of movie reviews into positive or negative polarities using two models: one with a SVM and other with a voting process between Naive Bayes, Multinomial Naive Bayes and Bernoulli Naive Bayes classifiers.
Technologies involved: Python (Nltk)
COMPUTER VISION
Multi-label apparel images prediction
Identifying type-color combination for 5 types and 6 colors of clothing’ images using a convolutional neural network (CNN).
Technologies involved: Python (Fastai)
The Simpsons image classification
Identifying 42 characters of ‘The Simpsons’ tv series using a convolutional neural network (CNN).
Technologies involved: Python (Fastai)
OTHERS
Contributions to projects required to graduate Udacity's NLP Nanodegree: