Content for Udacity's Machine Learning curriculum, which includes projects and their descriptions.
Projects included:
-
Boston Housing - I analysed past data of the cost of various houses in the Boston area alongside features about each property to make a model that can predict the price other houses can sell for. This was an introduction to using supervised machine learning techniques for me.
-
Finding Donors - This was a more advanced supervised machine learning project where I used a dataset to predict the kind of people who would be likely to donate to a particular charity.
-
Customer Segments - I analysed the spending habits of various types of consumers to group them into distinct categories (i.e. personal, cafe, restaurant, etc). This was an introduction to using unsupervised machine learning techniques.
-
Smartcab - This project was an introduction to reinforcement learning techniques, which I used to train a smartcab to drive around a simulated city environment, and make it safely to the goal within the allowed time. The car was originally trained by giving it a series of rewards/punishments based on the actions it took, whereby it gradually learned to understand the rules that safe driving requires.
-
Digit recognition - Use neural networks from TensorFlow to classify digits from not-MNIST data set.
-
Image classification - Use neural networks from TensorFlow to classify images.
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License. Please refer to Udacity Terms of Service for further information.
