Video Description
Sponsored by Amazon.
Deep learning neural networks have driven breakthrough results in computer vision, speech processing, machine translation, and reinforcement learning. As a result, neural networks have become an essential part of any data scientist’s toolkit. This course explains what neural networks are, why they are powerful algorithms, and why they have a particular structure. It begins by introducing the core components of a neural network (i.e., nodes, weights, biases, activation functions, and layers). Along the way, you'll learn about the backpropagation algorithm and how neural networks learn. Prerequisites include a basic understanding of linear algebra and calculus.
- Learn what deep learning neural networks are, what they're used for, and why they're powerful
- Discover the particular structure of neural networks and why it matters
- Explore the basic concepts used in building and training neural networks
- Develop a solid platform for learning more about deep learning and neural networks
Laura Graesser is assisting with NVIDIA's autonomous driving project. Previously with The Boston Consulting Group, Laura is a graduate student at New York University, where she's working toward a master’s degree in computer science and machine learning. Laura's interests include neural networks and their application to computer vision problems, and in the cross-fertilization between computer vision and natural language processing.
Table of Contents
- Introducing the Course 00:03:42
- What Are Neural Networks? 00:07:16
- Introducing Nodes, the Fundamental Building Blocks of Neural Networks 00:08:43
- Introducing the Structure of a Deep Feedforward Neural Network 00:05:01
- Why the Structure of a Neural Network Is Powerful—Motivating Example 00:04:23
- Why the Structure of a Neural Network Is Powerful—Layers and Nonlinearities 00:09:31
- How Neural Networks Learn—Loss Functions 00:05:49
- How Neural Networks Learn—Back Propagation and Gradient Descent 00:10:48