Course 806:
Foundations of Neural Networks and Deep Learning

(4 days)


Course Description

This course is for those who wish to learn about neural networks and deep learning technology and how they can be applied to real-world problems. Using real-world examples and minimal theory, the course helps attendees gain an intuitive understanding of the concepts and tools required to build deep neural network systems.

Learning Objectives

In this course, attendees will learn:

  • What neural networks and deep learning is and what they can realistically be used for
  • The basic theory of neural networks and machine learning
  • The architectures of neural networks including convolutional and recurrent
  • How to apply specific networks to the right problems
  • Use industry standard frameworks scikit-learn, TensorFlow, and Keras to build learning solutions


Basic knowledge of Python is assumed, and some exercises include writing code. However, if you are not a programmer, the exercises are structured so you can learn the key components of deep learning without programming if you chose. No assumptions are made about attendee mathematical backgrounds.

Course Outline

Introduction to Machine Learning

  • What Is Machine Learning?
  • Why Use Machine Learning?
  • Types of Machine Learning Systems
  • Challenges of Working with Machine Learning

 Core Learning Algorithms: Regression and Classification

  • Introducing Regression
  • Building a Linear Model
  • Non-Linear Data and Polynomial Models
  • Introducing Classification
  • Building a Classifier

 Machine Learning Tools

  • Overview of Machine Learning Tools
  • Introduction to TensorFlow
  • Introduction to scikit-learn
  • Comparing TensorFlow with scikit-learn

Introduction to Neural Networks

  • The Perceptron Model
  • How a Perceptron Learns
  • Building and Training a Single Perceptron

 Multilayer Perceptrons

  • The Architecture of Multilayer Perceptrons
  • Backpropagation and How It Works
  • Building a Multilayer Perceptron with TensorFlow

Convolutional Neural Networks

  • Introducing Convolutional Neural Networks (CNNs)
  • How CNNs Work
  • Building a CNN

Recurrent Neural Networks

  • Introducing Recurrent Neural Networks (RNNs)
  • How RNNs Work
  • Building a RNN

Other Network Architectures

  • Reinforcement Learning
  • Autoencoders
  • Recursive Networks
  • Ensembles

Please Contact Your ROI Representative to Discuss Course Tailoring!