This was my second machine learning project, and this was definitely demonstrated the capacity that Machine Learning has. This was a more complex dataset than the first project that I endeavored on, so the use of more complex models such as neural networks was appropriate. This data described the physical attributes of abalones, a type of shellfish. I first used the sex, length, diameter, height, rings features to predict whole-weight of an abalone. Again it seemed that a linear model seemed to outperform the neural network model. The second task that I performed was where I learned the most about Tensorflow (the Machine Learning API that I used for this project). This time I used all other features (omitting some redundant features for better accuracy), to predict the sex (Male, Female, or Infant) of the abalone. This proved to be a little more difficult, for there seemed to be no clear indication of what features seemed to be correlated to sex. In the end, I had an accuracy of around 50%, which is somewhat better than guessing, but not necessarily ground-breaking. It did make me feel better after some research that Eladio Rego's Abalone prediction also attempted to predict sex and got an accuracy of 53%. So it was not necessarily my model that was bad but was just that was very little correlation of sex and other features. I consider this project very successful in enabling me to learn the basics of Machine Learning and understand some of the processes behind it, such as the writing code and manipulating data.