Introduction to Neural Networks

Brought by: Brilliant

Overview

Artificial neural networks learn by detecting patterns in huge amounts of information. Much like your own brain, artificial neural nets are flexible, data-processing machines that make predictions and decisions. In fact, the best ones outperform humans at tasks like chess and cancer diagnoses.

In this course, you'll dissect the internal machinery of artificial neural nets through hands-on experimentation, not hairy mathematics. You'll develop intuition about the kinds of problems they are suited to solve, and by the end you’ll be ready to dive into the algorithms, or build one for yourself.

Syllabus

  • Introduction: When traditional AI hit a dead end, artificial neural nets jumped in.
    • Neural Networks: Teaching machines to teach themselves
    • The Computer Vision Problem: Think image recognition is easy? Try seeing in pixels.
    • The Folly of Computer Programming: Why do we need neural networks? Some things just can't be programmed.
    • Can Computers Learn?: Do you have to be living to be learning?
  • Neurons: The power of neural networks emerges from these simple building blocks.
    • The Decision Box: Meet your first artificial neuron and learn how to encode simple logical operations.
    • Activation Arithmetic: You can count on simple artificial neurons — literally.
    • Decision Boundaries: Hone your intuition with this graphical model of a binary neuron.
    • Building an XOR Gate: Escape the limitations of single neurons by stacking them in layers.
    • Classification: Sorting things into groups? The neuron knows best.
    • Sigmoid Neurons: Real data isn't black and white — this neuron sees in shades of gray.
    • Training a Single Neuron: Take a shot at building your first learning algorithm.
  • Layers: Connecting neurons together in layers boosts a neural net's performance.
    • Hidden Layers: Got some complex data to classify? Try adding a hidden layer to your ANN.
    • Curve Fitting: Classifying isn't an ANN's only schtick. They are used to model lots of different data.
    • Universal Approximator: Don't think an ANN can model it? Think again — they're universal.
    • A Shape-Recognizing Network: Learn how an ANN learns to see — and how you can trick it.
Introduction to Neural Networks
Go to course

Introduction to Neural Networks

Brought by: Brilliant

  • Brilliant
  • Paid
  • English
  • Certificate Not Available
  • Available at any time
  • beginner
  • N/A