Deep Learning What You'll Do

In this lesson, you'll learn how you can develop algorithms that are suitable to model high-level abstractions of data and create a type of "intelligence" that is able to use this abstraction for processing new information. First, you'll learn about deep neural networks — artificial neural networks that have multiple hidden layers of information between its input and output. Next, you'll learn about convolutional neural networks — a different flavor of neural networks that are modeled after biological processes like visual and aural feedback. Finally, you'll learn about deep models for sequence learning — models that can "understand" written and spoken language and text.

The underlying lesson from these concepts is that, with enough data and time to learn, we can develop intelligent agents that think and act in many of the same ways we as humans do. Being able to model complex human behaviors and tasks like driving a car, processing spoken language, or even building a winning strategy for the game of Go, is a task that could not be done without use of deep learning.