This repo for 365 Data Science Bootcamp projects
We'll apply all the knowledge from the lectures in this section to write a deep neural network. The problem we've chosen is referred to as the "Hello World" for machine learning because for most students it is their first example. The dataset is called MNIST and refers to handwritten digit recognition. You can find more about it on Yann LeCun's website (Director of AI Research, Facebook). He is one of the pioneers of what we've been talking about and of more complex approaches that are widely used today, such as covolutional networks. The dataset provides 28x28 images of handwritten digits (1 per image) and the goal is to write an algorithm that detects which digit is written. Since there are only 10 digits, this is a classification problem with 10 classes. In order to exemplify what we've talked about in this section, we will build a network with 2 hidden layers between inputs and outputs.
It relates to the audio versions of books ONLY. Each customer in the database has made a purchase at least once, that's why he/she is in the database. We want to create a machine learning algorithm based on our available data that can predict if a customer will buy again from the Audiobook company.
Explore if employee regularly staying away from work with a good reason or not.