Finished Udacity's Deep Learning Nanodegree, where I had lots of fun understanding and building deep learning models to do all sorts of things, like:
- Predictive Neural Network to analyze bike-sharing data and find usage patterns.
- Convolutional Neural Networks to classify images based on patterns and objects (faces, melanomas, etc).
- Recurrent Neural Networks to perform sentiment analysis on a given text (happy, sad, angry) and to generate new TV scripts.
-
Generative Adversarial Networks to generate realistic images of faces (humans that have never existed!!)