Deep Learning Essentials

Overview

Syllabus 4

1. Module 1: History of Deep Learning 3 hours

   In this module, we'll first peek through history, talk about the different ways in which people have attempted to build artificial intelligences in the past and explore what intelligence is made up of. Then, we'll start our investigation into an early model called the perceptron.

2. Module 2: Perceptron, Stochastic Gradient Descent & Kernel Methods 5 hours

   This module, we will continue exploring the perceptron. We'll delve into stochastic gradient descent (SGD), a fundamental optimization technique that enables the perceptron, and other models, to learn from data by iteratively updating the model's parameters to minimize errors. Afterward, we will lo…

3. Module 3: Fully Connected Networks 2.5 hours

   This module, we will move to exploring fully-connected networks. These networks are sophisticated models that can be thought of as a perceptron sitting on top of another perceptron, continuing in such a fashion. Each layer in a fully-connected network takes inputs from the layer below it, working t…

4. Module 4: Backpropagation 5 hours

   We will finish this course by looking at backpropagation, which is an algorithm to train neural networks to find the best set of weights that minimize error on the data. Backpropagation applies the chain rule from calculus to efficiently calculate gradients of the loss function with respect to the…

Advantages and disadvantages

Some points apply to every course of this kind; see how we rank.

Taught by

• Chris Callison-BurchAssociate Professor, Computer and Information Science
• Pratik ChaudhariAssistant Professor, Electrical and Systems Engineering