Sign in to report inappropriate content. Now that we've learned about the basic feed forward, fully connected, neural network, it's time to cover a new one: the convolutional neural network, often referred to as a convnet or cnn. Convolutional neural networks got their start by working with imagery.
The purpose of this project is to use Python to play Grand Theft Auto 5. There are many things to do in GTA V, but our first goal will be to create a self-driving car, well scooter in this case. The idea of using GTA V is that it is such a massive, open, sand-box type of environment that we can control, so it makes for a great development area. Using the methods we use here, you should be able to follow along with a different game as well, it's certainly not required that you use GTA V, but that's what I will be using.
Welcome to the 10th part of our of our machine learning regression tutorial within our Machine Learning with Python tutorial series. We've just recently finished creating a working linear regression model, and now we're curious what is next. Right now, we can easily look at the data, and decide how "accurate" the regression line is to some degree. What happens, however, when your linear regression model is applied within 20 hierarchical layers in a neural network? Not only this, but your model works in steps, or windows, of say 100 data points at a time, within a dataset of 5 million datapoints.