Differentially private python web applications

Learn how to deploy differentially private machine learning solutions in the matter of hours.
Rating: 3.9 out of 5 (21 ratings)
3,725 students
Differentially private python web applications
Rating: 3.9 out of 5 (21 ratings)
3,725 students
How to create differentially private (perserving information privacy) python web applications
How to quickly iterate and create minimum viable product (MVP)
How to embedd machine learning solutions in order to preserve privacy

Requirements

  • Python
  • Data Science
  • Machine Learning

Description

Please note that this is a FREE course, so the course does not cover certain topics extensivly because there is a 2 hour limit. In order for me to keep it FREE I needed to make some compromises on the depth of the content. I tried not to talk about stuff that you can find on internet for free.




Keeping it short and sweet, we will be focusing on these two topics:

1. How to deploy python web-apps in matter of hours, i.e. create fastly your minimum viable product MVP

2. Whats differential privacy, how does it work, how can we use it off the shelf and incroporate it in our machine learning solution?


We will be moving away from the jupyter-like development enviroment and start serving applications to the consumer.


Three aplications:

  1. Titanic challenge, the famous kaggle challenge will be served and start beeing accessible as a differentially private machine learning solution

  2. Road trip app, highly versatile app where we try to predict some event (in my case wether the road trip will take place or not) given the weather forecast. But you can use my code from github and modify it to your organisations variant.

  3. Corona webapp. Given the new situation with this pandemic, we showcased how can you create a product (mortality application) very quickly, and adjust and potentially help people.

For more detailed content and in dept information check out Manuel Amunategui and the ViralML show.

Who this course is for:

  • All python enthusiasts, with enough motivation to look up certain concepts

Course content

4 sections • 8 lectures • 1h 50m total length
  • Introduction
    03:48
  • Differential privacy
    14:05

Instructor

Machine Learning Engineer
Noah Weber
  • 3.8 Instructor Rating
  • 41 Reviews
  • 7,200 Students
  • 3 Courses

My name is Noah. I'm a machine learning engineer from Austria. Trained as a mathematican I've been writing code for 6 years, and for the past three years, I've focused on writing machine learning applications. I've done this at banks and fintech companies, where I've worked on and grown production machine learning applications used by hundreds of thousands of people. I've built and maintained machine learning systems which make credit-risk and fraud detection judgements on over a billion dollars per year.

I'm also passionate about helping others tackle their own problems in machine learning area. You can find me answering questions on stackexhange, or competing on kaggle.