Deep Learning Prerequisites: Logistic Regression in Python
4.6 (2,862 ratings)
22,994 students enrolled

# Deep Learning Prerequisites: Logistic Regression in Python

Data science techniques for professionals and students - learn the theory behind logistic regression and code in Python
Bestseller
4.6 (2,862 ratings)
22,994 students enrolled
Last updated 3/2020
English
English [Auto-generated], Portuguese [Auto-generated], 1 more
Current price: \$104.99 Original price: \$149.99 Discount: 30% off
5 hours left at this price!
30-Day Money-Back Guarantee
This course includes
• 6 hours on-demand video
• Access on mobile and TV
• Certificate of Completion
Training 5 or more people?

What you'll learn
• program logistic regression from scratch in Python
• describe how logistic regression is useful in data science
• derive the error and update rule for logistic regression
• understand how logistic regression works as an analogy for the biological neuron
• use logistic regression to solve real-world business problems like predicting user actions from e-commerce data and facial expression recognition
• understand why regularization is used in machine learning
Course content
Expand all 57 lectures 05:57:24
+ Start Here
4 lectures 18:00

This lecture will outline what will be learned in the course. I explain the importance of knowing the math, and provide short descriptions of each section later covered. Feel free to skip it and jump right into the 3rd video.

Preview 04:02

Difference between supervised and unsupervised learning. Difference between classification and regression. Feel free to skip this one if you already know this.

Preview 01:53
Introduction to the E-Commerce Course Project
08:52

An easy first quiz

Easy first quiz
1 question
+ Basics: What is linear classification? What's the relation to neural networks?
9 lectures 33:44

I discuss what linear classification is from a general standpoint, without invoking any specifics related to logistic regression. I provide a 2-dimensional binary classification example and go over how we would classify data into 1 of 3 cases: positive class, negative class, and don't know / not sure.

Linear Classification
04:49

In this lecture I discuss a brief history of neural networks, and talk about how the characteristics of the neuron (action potential, signal propagation, inhibitory and excitatory behavior) are modeled in different ways: the Hodgkin Huxley mdoel, the FitzHugh Nagumo model, and the logistic model.

Preview 03:36

I show the feedforward calculation for the output of a logistic unit.

How do we calculate the output of a neuron / logistic classifier? - Theory
04:18

I show how to code the feedforward calculation for the output of a logistic unit in Python and numpy.

How do we calculate the output of a neuron / logistic classifier? - Code
04:30
Interpretation of Logistic Regression Output
05:32
E-Commerce Course Project: Pre-Processing the Data
05:24
E-Commerce Course Project: Making Predictions
03:00
Feedforward Quiz
01:24
Prediction Section Summary
01:11
+ Solving for the optimal weights
11 lectures 46:13
Training Section Introduction
01:38

I show how we can solve for the weights in a logistic regression model if we make assumptions about the distributions of the input data (equal variance, Gaussian-distributed).

A closed-form solution to the Bayes classifier
05:59

All these symbols can get confusing so this is a lecture to give a short and simple description of what each letter "stands for". These are important to get right now, because we'll use it for this course and every later course on deep learning and machine learning.

What do all these symbols mean? X, Y, N, D, L, J, P(Y=1|X), etc.
03:37

I show the cross-entropy error formula, and describe why this is used as an appropriate objective function for logistic regression.

The cross-entropy error function - Theory
02:46

I show how to calculate the cross-entropy error of your model in Python and numpy.

The cross-entropy error function - Code
04:53
Visualizing the linear discriminant / Bayes classifier / Gaussian clouds
02:28

I show how to derive the likelihood and log-likelihood of your model and data, and I show how maximizing the likelihood is equivalent to minimizing the cross-entropy.

Maximizing the likelihood
06:34

I explain how gradient descent can be used to solve for the minima of a function, and the algorithm that can be used to iteratively update the logistic weights.

Updating the weights using gradient descent - Theory
06:20

I show how to code weight updates for logistic regression using gradient descent in Python and numpy.

Updating the weights using gradient descent - Code
03:09
E-Commerce Course Project: Training the Logistic Model
06:47
Training Section Summary
02:02
+ Practical concerns
11 lectures 54:11
Practical Section Introduction
02:45
Interpreting the Weights
04:07
L2 Regularization - Theory
08:38

I show how to apply regularization for logistic regression in Python.

L2 Regularization - Code
01:43
L1 Regularization - Theory
02:53
L1 Regularization - Code
06:13
L1 vs L2 Regularization
03:05

I show how logistic regression can be used to solve the donut problem (where one class is circular and is inside another circular class).

The donut problem
10:01

This lecture describes how to apply logistic regression to the XOR problem by making it a 3-dimensional problem.

The XOR problem
06:12
Why Divide by Square Root of D?
06:32
Practical Section Summary
02:02
+ Checkpoint and applications: How to make sure you know your stuff
2 lectures 08:01

This is a clip from my natural language processing course. It shows you how to apply logistic regression to sentiment analysis - measuring how positive or negative a word is.

BONUS: Sentiment Analysis
05:13
BONUS: Exercises + how to get good at this
02:48
+ Project: Facial Expression Recognition
6 lectures 40:59
Facial Expression Recognition Project Introduction
04:51
Facial Expression Recognition Problem Description
12:21
The class imbalance problem
06:01
Utilities walkthrough
05:45
Facial Expression Recognition in Code
10:41
Facial Expression Recognition Project Summary
01:20
+ Appendix / FAQ
14 lectures 02:36:16
What is the Appendix?
02:48
04:30
Windows-Focused Environment Setup 2018
20:20
How to install Numpy, Scipy, Matplotlib, Pandas, IPython, Theano, and TensorFlow
17:32
How to Code by Yourself (part 1)
15:54
How to Code by Yourself (part 2)
09:23
How to Uncompress a .tar.gz file
03:18
How to Succeed in this Course (Long Version)
10:24
Is this for Beginners or Experts? Academic or Practical? Fast or slow-paced?
22:04
Proof that using Jupyter Notebook is the same as not using it
12:29
Python 2 vs Python 3
04:38
What order should I take your courses in? (part 1)
11:18
What order should I take your courses in? (part 2)
16:07
BONUS: Where to get discount coupons and FREE deep learning material
05:31
Requirements
• Derivatives, matrix arithmetic, probability
• You should know some basic Python coding with the Numpy Stack
Description

This course is a lead-in to deep learning and neural networks - it covers a popular and fundamental technique used in machine learning, data science and statistics: logistic regression. We cover the theory from the ground up: derivation of the solution, and applications to real-world problems. We show you how one might code their own logistic regression module in Python.

This course does not require any external materials. Everything needed (Python, and some Python libraries) can be obtained for free.

This course provides you with many practical examples so that you can really see how deep learning can be used on anything. Throughout the course, we'll do a course project, which will show you how to predict user actions on a website given user data like whether or not that user is on a mobile device, the number of products they viewed, how long they stayed on your site, whether or not they are a returning visitor, and what time of day they visited.

Another project at the end of the course shows you how you can use deep learning for facial expression recognition. Imagine being able to predict someone's emotions just based on a picture!

If you are a programmer and you want to enhance your coding abilities by learning about data science, then this course is for you. If you have a technical or mathematical background, and you want use your skills to make data-driven decisions and optimize your business using scientific principles, then this course is for you.

This course focuses on "how to build and understand", not just "how to use". Anyone can learn to use an API in 15 minutes after reading some documentation. It's not about "remembering facts", it's about "seeing for yourself" via experimentation. It will teach you how to visualize what's happening in the model internally. If you want more than just a superficial look at machine learning models, this course is for you.

Suggested Prerequisites:

• calculus (taking derivatives)

• matrix arithmetic

• probability

• Python coding: if/else, loops, lists, dicts, sets

TIPS (for getting through the course):

• Watch it at 2x.

• Take handwritten notes. This will drastically increase your ability to retain the information.

• Write down the equations. If you don't, I guarantee it will just look like gibberish.

• Ask lots of questions on the discussion board. The more the better!

• Realize that most exercises will take you days or weeks to complete.

• Write code yourself, don't just sit there and look at my code.

WHAT ORDER SHOULD I TAKE YOUR COURSES IN?:

• Check out the lecture "What order should I take your courses in?" (available in the Appendix of any of my courses, including the free Numpy course)

Who this course is for:
• Adult learners who want to get into the field of data science and big data
• Students who are thinking of pursuing machine learning or data science
• Students who are tired of boring traditional statistics and prewritten functions in R, and want to learn how things really work by implementing them in Python
• People who know some machine learning but want to be able to relate it to artificial intelligence
• People who are interested in bridging the gap between computational neuroscience and machine learning