• You must be logged in to view that page
  • You must be logged in to view that page

Artificial Neural Networks View more

A quick dive into a cutting-edge computational method for learning.

Book 28 Lessons

Learning and the Brain

Start

Learning Problems for Neural Networks

Computationally Modeling The Brain

Computational Models of The Neuron

Math for Neural Networks

Vectors for Neural Networks

Matrices for Neural Networks

Optimization for Neural Networks

Perceptrons

Perceptrons as Linear Classifiers

Perceptron Learning Algorithm

Dealing with Perceptron Limitations

Multilayer Perceptrons

Basics and Motivation

Practical Example

Multilayer Perceptron - Model Complexity

Backpropagation

Gradient Descent

Backpropagation - Updating Parameters

Backpropagation

Vanishing and Exploding Gradient

Convolutional Neural Networks

Convolutional Neural Networks - Overview

Convolutions and Striding

Convolutional Neural Networks - Pooling

Applications and Performance

Recurrent Neural Networks

Recurrent Neural Networks

Training Recurrent Neural Networks

Long Short-Term Memory

Advanced Architectures

Stochastic Neural Networks

Generative Adversarial Networks

Variational Autoencoders

Word2Vec

Reinforcement Learning

Course description

This course was written in collaboration with machine learning researchers and lecturers from MIT, Princeton, and Stanford.

This interactive course dives into the fundamentals of artificial neural networks, from the basic frameworks to more modern techniques like adversarial models.

Topics covered

  • Adversarial Networks
  • Backpropagation
  • Convolutional Networks
  • Gradient Descent
  • Linear Classifiers
  • LSTM
  • Optimization
  • Perceptron
  • Recurrent Networks
  • Reinforcement Learning
  • Stochastic Networks
  • Variational Autoencoders

Prerequisites and next steps

You'll need mastery of algebra. A basic understanding of calculus and probability will be helpful.

Prerequisites

Next steps