Interactive Course

Artificial Neural Networks

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



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

You’ll answer questions such as how a computer can distinguish between pictures of dogs and cats, and how it can learn to play great chess.

Topics covered

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

Interactive quizzes


Concepts and exercises


Course map

Prerequisites and Next Steps

  1. 1

    Learning and the Brain

    To build an artificial learning algorithm, start with the human brain.

    1. Learning Problems for Neural Networks

      Get a big-picture sense of what learning problems are all about.

    2. Computationally Modeling The Brain

      Learn how the human brain inspires the mechanisms within ANNs.

    3. Computational Models of The Neuron

      Build a computational model of a neuron and explore why it is so powerful.

  2. 2

    Math for Neural Networks

    A refresher on vectors, matrices, and optimization.

    1. Vectors for Neural Networks

      A quick overview of vectors, which are used to represent inputs and weights in an ANN.

    2. Matrices for Neural Networks

      Matrices help simplify algorithm representation, and in practice can speed up performance.

    3. Optimization for Neural Networks

      Derivatives play a key role in optimizing model parameters, such as weights and biases.

  3. 3


    The building block of many neural networks.

    1. Perceptrons as Linear Classifiers

      Get a sense of why perceptron is a linear classifier, and explore its strengths and limitations.

    2. Perceptron Learning Algorithm

      Build up the learning algorithm for perceptron, and learn how to optimize it.

    3. Dealing with Perceptron Limitations

      Dive deeper into the limitations of perceptron, and explore how to overcome some of them.

  4. 4

    Multilayer Perceptrons

    Stringing it all together.

    1. Basics and Motivation

      Learn how to transform data so that it becomes linearly separable.

    2. Practical Example

      Behold the power of multilayer perceptrons, applied to a sportswear marketing problem.

    3. Multilayer Perceptron - Model Complexity

      How can you measure how complex a model is, and avoid unnecessary complexion?

    4. Avoiding Overfitting

      Neural networks are vulnerable to overfitting. Here’s how to avoid it!

  5. 5


    Using a model's outputs to train it to do even better.

    1. Gradient Descent

      Master this powerful tool for optimization problems, such as minimizing loss.

    2. Backpropagation - Updating Parameters

      Learn how we can update parameters — even those that are in hidden layers!

    3. Backpropagation

      For gradient descent, you’ll need this tool for efficiently computing the gradient of an error function.

    4. Vanishing and Exploding Gradient

      If you’re not careful, an activation function can squash or amplify gradients.

  6. 6

    Convolutional Neural Networks

    Models to capture structural information within data.

    1. Convolutional Neural Networks - Overview

      These networks excel in image classification problems, even achieving better-than-human performance!

    2. Convolutions and Striding

      Explore convolutions, padding, and striding — the mathematical nuts and bolts behind feature maps.

    3. Convolutional Neural Networks - Pooling

      Learn how to downsample an image, while retaining enough information to recognize rich objects.

    4. Applications and Performance

      A tour of real-world applications, from text-to-speech to artistic style transfer!

  7. 7

    Recurrent Neural Networks

    Models to process sequential data by remembering what we already know.

    1. Recurrent Neural Networks

      Explore this powerful model for data that isn’t independent, such as words in a sentence.

    2. Training Recurrent Neural Networks

      Learn how to train a RNN using back propagation through time.

    3. Long Short-Term Memory

      Long short-term memories “remember” the past much better than simple RNNs.

  8. 8

    Advanced Architectures

    A look into stochastic ANNs, adversarial techniques, vectorization, and other advanced topics.

    1. Stochastic Neural Networks

      Explore better models for stochastic processes, such as stock prices or the weather.

    2. Generative Adversarial Networks

      How can a neural network generate realistic looking fake humans?

    3. Variational Autoencoders

      This variation on GANs is sometimes even more powerful.

    4. Word2Vec

      Learn how words can be vectorized to represent their relative relationships.

    5. Reinforcement Learning

      Reinforcement isn’t just for humans - it’s the training behind AlphaGo and other cutting-edge achievements.