Machine Learning: deep learning & neural networks with TensorFlow

In this course we will learn the different aspects of Machine Learning (ML). We will begin by looking into the different problems that we can solve with ML and when and why we must use ML.

This course handles advanced Machine Learning models such as deep neural networks (deeplearning). We will put this knowledge into practice by building our own deep neural networks in Python with the TensorFlow library.

Schedule

No public sessions are currently scheduled. We will be pleased to set up an on-site course or to schedule an extra public session (in case of a sufficient number of candidates). Interested? Please let us know.

Intended for

Anyone that wants to use machine learning to solve real-life problems.

Background

Good Python programming knowledge is a prerequisite (see Python fundamentals). Basic understanding of Machine Learning is also essential (see Machine Learning fundamentals using Python).

Main topics

  • Basic concepts of deep learning
  • Input layer
  • Hidden layer
  • Output layer
  • Weights
  • Bias
  • Forward propagation
  • Activation functions
  • Softmax
  • Gradient descent
  • Backpropagation
  • Drop-out
  • Regularization
  • The different models of deep learning
  • Deep neural network
  • Convolutional neural network
  • Recurrent neural network
  • Building deep neural networks with TensorFlow

Training method

Classroom teaching, focused on practical examples and supported by in-depth exercises and individual practice.

Duration

3 days.

Course leader

ML6.


SESSION INFO AND ENROLMENT