Back to all courses

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.

Interactive
quizzes

29

Concepts and
exercises

250+
  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. Included with
      Brilliant Premium

      Vectors for Neural Networks

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

    2. Included with
      Brilliant Premium

      Matrices for Neural Networks

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

    3. Included with
      Brilliant Premium

      Optimization for Neural Networks

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

  3. 3

    Perceptrons

    The building block of many neural networks.

    1. Included with
      Brilliant Premium

      Perceptrons as Linear Classifiers

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

    2. Included with
      Brilliant Premium

      Perceptron Learning Algorithm

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

    3. Included with
      Brilliant Premium

      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. Included with
      Brilliant Premium

      Basics and Motivation

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

    2. Included with
      Brilliant Premium

      Practical Example

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

    3. Included with
      Brilliant Premium

      Multilayer Perceptron - Model Complexity

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

    4. Included with
      Brilliant Premium

      Avoiding Overfitting

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

  5. 5

    Backpropagation

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

    1. Included with
      Brilliant Premium

      Gradient Descent

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

    2. Included with
      Brilliant Premium

      Backpropagation - Updating Parameters

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

    3. Included with
      Brilliant Premium

      Backpropagation

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

    4. Included with
      Brilliant Premium

      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. Included with
      Brilliant Premium

      Convolutional Neural Networks - Overview

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

    2. Included with
      Brilliant Premium

      Convolutions and Striding

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

    3. Included with
      Brilliant Premium

      Convolutional Neural Networks - Pooling

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

    4. Included with
      Brilliant Premium

      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. Included with
      Brilliant Premium

      Recurrent Neural Networks

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

    2. Included with
      Brilliant Premium

      Training Recurrent Neural Networks

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

    3. Included with
      Brilliant Premium

      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. Included with
      Brilliant Premium

      Stochastic Neural Networks

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

    2. Included with
      Brilliant Premium

      Generative Adversarial Networks

      How can a neural network generate realistic looking fake humans?

    3. Included with
      Brilliant Premium

      Variational Autoencoders

      This variation on GANs is sometimes even more powerful.

    4. Included with
      Brilliant Premium

      Word2Vec

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