Sorry, your browser is not supported
To have the best experience using Skillshare, we recommend that you use one of these supported browsers.

Deep Learning and Neural Networks with Python

Frank Kane, Founder of Sundog Education, ex-Amazon

Play Speed
  • 0.5x
  • 1x (Normal)
  • 1.25x
  • 1.5x
  • 2x
16 Videos (2h 42m)
    • Course Introduction

    • Getting Started and Prerequisites

    • The History of Artificial Neural Networks

    • Hands-On in the Tensorflow Playground

    • Deep Learning Details

    • Introducing Tensorflow

    • Using Tensorflow for Handwriting Recognition (part 1)

    • Using Tensorflow for Handwriting Recognition (part 2)

    • Introducing Keras

    • Using Keras to Learn Political Affiliations

    • Convolutional Neural Networks

    • Using CNN's for Handwriting Recognition

    • Recurrent Neural Networks

    • Using RNN's for Sentiment Analysis

    • The Ethics of Deep Learning

    • Deep Learning: Learning More

43 students are watching this class

About This Class

It's hard to imagine a hotter technology than deep learning, artificial intelligence, and artificial neural networks. If you've got some Python experience under your belt, this course will de-mystify this exciting field with all the major topics you need to know. 

We'll cover:

  • Artificial Neural Networks
  • Multi-Layer Perceptions
  • Tensorflow
  • Keras
  • Convolutional Neural Networks
  • Recurrent Neural Networks

And it's not just theory! In addition to the class project, as you go you'll get hands-on with some smaller activities and exercises:

  • Building neural networks for handwriting recognition
  • Learning how to predict a politician's political party based on their votes
  • Performing sentiment analysis on real movie reviews
  • Interactively constructing deep neural networks and experimenting with different topologies

A few hours is all it takes to get up to speed, and learn what all the hype is about. If you're afraid of AI, the best way to dispel that fear is by understanding how it really works - and that's what this course delivers.


15 of 15 students recommendSee All

Very broad and informative class, great pace and Frank pays good attention to key details.
This is a great class. It is very concise and easy to understand. I find myself reusing the samples as templates for my own NN now and I've recommended the class to my friends as you can quickly learn Neural Networks as well as become familiar with python and notebook. Lots of non-video material to play around with. My only nitpicky criticism ,if the teacher wanted to improve this class, was that the RNN example was not thorough enough. The example was pre-formated to numerical indexes and the example only showed using one block of text for predictions but not what to do if you have other variables that you want to consider along with that block. I'd like to see a second RNN example using a less pre-processed dataset and complex example. I only say this because the NN and CNN examples were so good I was able to easily able to template them to completely new datasets as a good starting off point for my own NNs. However, for RNNs, I had no idea how to do the text preprocessing or deal with multiple variables so I could not start making functional RNNs without much more study. That would be a lot to show in one example but if the teacher wanted to add a second RNN example video that would make this class even better. :-)





Frank Kane

Founder of Sundog Education, ex-Amazon

Frank spent 9 years at Amazon and IMDb, developing and managing the technology that automatically delivers product and movie recommendations to hundreds of millions of customers, all the time. Frank holds 17 issued patents in the fields of distributed computing, data mining, and machine learning. In 2012, Frank left to start his own successful company, Sundog Software, which focuses on virtual reality environment technology, and teaching others about big data analysis.

See full profile