Machine Learning for (smart) dummies

13:30-17:00, January 26

Workshop / Overview

Do you have a basic understanding of machine learning, but you have never actually got your hands dirty and started training a neural network? If yes, this workshop is the right choice for you!

We will take you on a 3-hour journey starting with a simple algorithm (linear regression). We will add layers of complexity to the algorithm in progressive steps, making it more powerful and able to tackle more advanced problems.

Around 70% of the workshop is dedicated to hands-on sessions on Python notebooks (Colaboratory). Don’t let Python scare you! These hands-on sessions are designed to suit different profiles of participants from coding beginners to expert developers. In fact, the participants can choose different levels of difficulty. Either code the algorithms from scratch, write parts of it, or just run a piece of code which already works and modify its parameters.

In the last part of the workshop, you will create, train and test a model to digitise a hand-written questionnaire. You will test the effectiveness of your own model by scanning the questionnaires with your phone, run your code and check how well it works.

This workshop is designed for professionals who have a data analysis background and at least a minimal programming experience (in VBA for example). This includes managers and executives from the industry who want to get their hands dirty, but also attendees with a technical background (with scientific masters or PhDs) who have never worked on machine learning directly.

Workshop / Outcome

By the end of the workshop, participants will be familiar with few selected machine learning algorithms: linear and logistic regression, multi-layer perceptron and convolutional neural networks. They will have a high-level understanding of the complexity behind these algorithms.

Attendees will create or modify lines of code and test the effect on the overall process running in the notebooks. In this way, participants will experience first-hand the potential and the limitations of these machine learning techniques.

Workshop / Difficulty

Beginner level

Workshop / Prerequisites

  • Experience in data analysis
  • Beginner level in a programming language (Python, VBA, C++, R, or Matlab for example)
  • Own laptop with modern browser

Track / Co-organizers

Valerio Rossetti

Co-Founder, SamurAI

AMLD EPFL 2020 / Workshops

A Conceptual Introduction to Reinforcement Learning

With Kevin Smeyers, Katrien Van Meulder & Bram Vandendriessche

09:00-12:30 January 25

Applied Machine Learning with R

With Dirk Wulff, Markus Steiner & Michael Schulte-Mecklenbeck

09:00-17:00 January 25

Augmenting the Web browsing experience using machine learning

With Oleksandr Paraska, Vasily Kuznetsov, Tudor Avram & Levan Tsinadze

09:00-12:30 January 25

AMLD / Global partners