Data Science: Deep Learning in Python

What Will I Learn?

• Learn how Deep Learning REALLY works (not just some diagrams and magical black box code)
• Learn how a neural network is built from basic building blocks (the neuron)
• Code a neural network from scratch in Python and numpy
• Code a neural network using Google's TensorFlow
• Describe different types of neural networks and the different types of problems they are used for
• Derive the backpropagation rule from first principles
• Create a neural network with an output that has K > 2 classes using softmax
• Describe the various terms related to neural networks, such as "activation", "backpropagation" and "feedforward"
• Install TensorFlow

Requirements

• How to take partial derivatives and log-likelihoods (ex. finding the maximum likelihood estimations for a die)
• Install Numpy and Python (approx. latest version of Numpy as of Jan 2016)
• Don't worry about installing TensorFlow, we will do that in the lectures.
• Being familiar with the content of my logistic regression course (cross-entropy cost, gradient descent, neurons, XOR, donut) will give you the proper context for this course

Who is the target audience?

• Students interested in machine learning - you'll get all the tidbits you need to do well in a neural networks course
• Professionals who want to use neural networks in their machine learning and data science pipeline. Be able to apply more powerful models, and know its drawbacks.
• People who already know how to take partial derivatives and log-likelihoods. Since we cover this in more detail in my logistic regression class, it is not covered quite as thoroughly here.
• People who already know how to code in Python and Numpy. You will need some familiarity because we go through it quite fast. Don't worry, it's not that hard.

Includes:

• 8.5 hours on-demand video
• Full lifetime access
• Access on mobile and TV
• Certificate of Completion

---

Take this course