Deep Learning, Neural Networks and TensorFlow

Preference Dates Timing Location
Evening Course 04 - 15 November 2018 (10 Sessions) 07:00PM - 10:00PM Dubai Knowledge Park
Daytime Course 25 - 29 November 2018 (5 Days) 10:00AM - 04:00PM Dubai Knowledge Park

Course Description

If you want to break into AI, this course will help you do so. Deep Learning is one of the most highly sought after skills in the IT industry.

This course will teach you the foundations of Deep Learning, understand how to build neural networks, and learn how to lead successful machine learning projects. You will learn about Convolutional networks, RNNs, LSTM, Adam, Dropout, BatchNorm, Xavier/He initialization, and more. You will work on case studies from health-care, autonomous driving, sign language reading, music generation, and natural language processing. You will master not only the theory, but also see how it is applied in industry. You will practice all these ideas in Python and in TensorFlow framework.

Unit 1 – Introduction to Deep Learning

  • What is Deep Learning
  • Trends driving the rise of Deep Learning
  • Practical Applications of Deep Learning
  • What is a Neural Network?
  • Supervised Learning with Neural Networks
  • Why is Deep Learning taking off?
  • Practical Project: Introduction to Deep Learning

Unit 2 – Neural Networks Basics

  • Binary Classification
  • Logistic Regression
  • Logistic Regression Cost Function
  • Gradient Descent
  • Derivatives
  • Computation graph
  • Derivatives with a Computation Graph
  • Vectorization
  • Broadcasting in Python
  • Practical Project: Creating a Logistic Regression Image Classifier

Unit 3 – Shallow Neural Networks

  • Neural Network Representation
  • Computing a Neural Network’s Output
  • Vectorizing across Multiple Examples
  • Activation Functions
  • Non-linear Activation Functions
  • Derivatives of Activation Functions
  • Gradient Descent for Neural Networks
  • Neural Network Backpropagation
  • Random Parameter Initialization
  • Practical Project: Data Cassification with one Hidden Layer

Unit 4 – Deep Neural Networks

  • Deep L-layer Neural Network
  • Forward Propagation in a Deep Network
  • Motivation behind Deep Representations
  • Building Blocks of Deep Neural Networks
  • Backpropagation in a Deep Neural Network
  • Understanding Parameters and Hyperparameters
  • Practical Project: Building a Deep Neural Network Application

Unit 5 – TensorFlow Basics

  • Introduction to TensorFlow
  • TensorFlow Basic Syntax
  • TensorFlow Graphs
  • Variables and Placeholders
  • TensorFlow Regression Example
  • TensorFlow Classification Example
  • Saving and Restoring Models
  • Practical Project: Developing a Classifier for MNIST Dataset with TensorFlow

Unit 6 – Convolutional Neural Networks

  • Convolutional neural networks structure
  • Different convolutional neural networks layers and their importance
  • Arrangement of spatial parameters
  • How and when to use stride and zero-padding
  • CNN model training process
  • How to build a convolutional neural network
  • Generating predictions and calculating loss functions
  • How to train and evaluate your MNIST classifier
  • How to build a simple image classification CNN

Unit 7 – Recurrent Neural Networks

  • RNN Theory
  • Manual Creation of RNN
  • Vanishing Gradients
  • LSTM and GRU
  • RNN with TensorFlow
  • Time Series Exercise
  • Word2Vec Theory
  • Word2Vec Example
  • Professionals or students who are interested in deep learning, and already have Python Programming and machine learning experience.
  • Future Data Science Professionals and Engineers
  • Intermediate Python programmers interested in enhancing their existing skills.

Python Programming Experience
Python for Data Science and Machine Learning

The participants who have successfully completed this course will be able to develop deep learning applications: including natural language processing and image recognition.

Testimonials