# Deep Learning with TensorFlow

#### Course Features

#### Course Details

**Course Objectives****Define Deep Learning**

**After the completion of this Deep Learning with TensorFlow course, you should be able to:**Express the motivation behind Deep Learning

Apply Analytical mathematics on the data

Choose between different Deep networks

Explain Neural networks

Train Neural networks

Discuss Backpropagation

Describe Autoencoders and varitional Autoencoders

Run a “Hello World” program in TensorFlow

Implement different Regression models

Describe Convolutional Neural Networks

Discuss the application of Convolutional Neural Networks

Discuss Recurrent Neural Networks

Describe Recursive Neural Tensor Network Theory

Implement Recursive Neural Network Model

Explain Unsupervised Learning

Discuss the applications of Unsupervised Learning

Explain Restricted Boltzmann Machine

Implement Collaborative Filtering with RBM

Define Autoencoders and discuss their Applications

Discuss Deep Belief Network

**Why learn Tensorflow?**

TensorFlow is one of the best libraries to implement Deep Learning. TensorFlow is a software library for numerical computation of mathematical expressions, using data flow graphs. Nodes in the graph represent mathematical operations, while the edges represent the multidimensional data arrays (tensors) that flow between them. It was created by Google and tailored for Machine Learning. In fact, it is being widely used to develop solutions with Deep Learning. Machine learning is one of the fastest-growing and most exciting fields out there, and Deep Learning represents its true bleeding edge. Deep learning is primarily a study of multi-layered neural networks, spanning over a vast range of model architectures. Traditional neural networks relied on shallow nets, composed of one input, one hidden layer and one output layer. Deep-learning networks are distinguished from these ordinary neural networks having more hidden layers, or so-called more depth. These kinds of nets are capable of discovering hidden structures within unlabeled and unstructured data (i.e. images, sound, and text), which constitutes the vast majority of data in the world.

**Who should go for this training?**

IteanzDeep learning with Tensorflow course is designed for all those who want to learn Deep Leaning which would include understanding of Deep Learning methods, Neural Networks, Deep Learning uses Tensorflow, Restricted Boltzmann Machines (RBM) and Autoencoders.

**The following professionals can go for this course:**

1. Developers aspiring to be a 'Data Scientist'

2. Analytics Managers who are leading a team of analysts

3. Business Analysts who want to understand Deep Learning (M.L) Techniques

4. Information Architects who want to gain expertise in Predictive Analytics

5. Professionals who want to captivate and analyze Big Data

6. Analysts wanting to understand Data Science methodologies

However, Deep learning is not just focused to one particular industry or skill set, it can be used by anyone to enhance their portfolio.

**What are the pre-requisites for this course?**

Required Pre-requisites

Basic programming knowledge in Python

Concept of Arrays

Concepts about Machine Learning

Iteanz offers you a complimentary self-paced course - A Module on Stats and Machine learning algorithms: Supervised and Unsupervised learning algorithms, once you have enrolled in Deep Learning with TensorFlow course

**Curriculum**

**Introduction to Deep Learning**

>

**Objectives:**

**At the end of this Module, you should be able to:**

Discuss the revolution of Artificial Intelligence

Discuss the limitations of Machine Learning

List the advantages of Deep Learning over Machine Learning

Discuss Real-life use cases of Deep Learning

Understand the Scenarios where Deep Learning is applicable

Discuss relevant topics of Linear Algebra and Statistics

Discuss Machine learning algorithms

Define Reinforcement Learning

Discuss model parameters and optimization techniques

**Topics:**

Deep Learning: A revolution in Artificial Intelligence

Limitations of Machine Learning

Discuss the idea behind Deep Learning

Advantage of Deep Learning over Machine learning

3 Reasons to go Deep

Real-Life use cases of Deep Learning

Scenarios where Deep Learning is applicable

The Math behind Machine Learning: Linear Algebra

Scalars

Vectors

Matrices

Tensors

Hyperplanes

The Math Behind Machine Learning: Statistics

Probability

Conditional Probabilities

Posterior Probability

Distributions

Samples vs Population

Resampling Methods

Selection Bias

Likelihood

Review of Machine Learning Algorithms

Regression

Classification

Clustering

Reinforcement Learning

Underfitting and Overfitting

Optimization

Convex Optimization

**Fundamentals of Neural Networks**

**Objectives:**

Discuss the Training Techniques of Neural Networks

List Different Activation and Loss Functions

Discuss the Different parameters of Neural Networks

**Topics:**

Defining Neural Networks

The Biological Neuron

The Perceptron

Multi-Layer Feed-Forward Networks

Training Neural Networks

Backpropagation Learning

Gradient Descent

Stochastic Gradient Descent

Quasi-Newton Optimization Methods

Generative vs Discriminative Models

Activation Functions

Linear

Sigmoid

Tanh

Hard Tanh

Softmax

Rectified Linear

Loss Functions

Loss Function Notation

Loss Functions for Regression

Loss Functions for Classification

Loss Functions for Reconstruction

Hyperparameters

Learning Rate

Regularization

Momentum

Sparsity

**Fundamentals of Deep Networks**

**Objectives:**

At the end of this Module, you should be able to:

Define Deep Learning

Discuss the Architectural Principals of Deep Networks

List Different parameters of Deep Networks

Discuss the Building Blocks of Deep Networks

Discuss how reinforcement learning is used in Deep Networks

**Topics:**

Defining Deep Learning

Defining Deep Networks

Common Architectural Principals of Deep Networks

Reinforcement Learning application in Deep Networks

Parameters

Layers

Activation Functions - Sigmoid, Tanh, ReLU

Loss Functions

Optimization Algorithms

Hyperparameters

Summary

**Introduction to TensorFlow**

**Objectives:**

**At the end of this Module, you should be able to:**

Define TensorFlow

Illustrate how TensorFlow works

Discuss the Functionalities of TensorFlow

Illustrate different ways to install TensorFlow

Write and Run programs on TensorFlow

**Topics:**

What is TensorFlow?

Use of TensorFlow in Deep Learning

Working of TensorFlow

How to install Tensorflow

HelloWorld with TensorFlow

Running a Machine learning algorithms on TensorFlow

**Convolutional Neural Networks (CNN)**

**Objectives:**

**At the end of this Module, you should be able to:**

Define CNNs

Discuss the Applications of CNN

Explain the Architecture of a CNN

List Convolution and Pooling Layers in CNN

Illustrate CNN

Discuss Fine-tuning and Transfer Learning of CNNs

**Topics:**

CNNs Application

Architecture of a CNN

Convolution and Pooling layers in a CNN

Understanding and Visualizing a CNN

Transfer Learning and Fine-tuning Convolutional Neural Networks

**Recurrent Neural Networks (RNN)**

**Objectives:**

**you should be able to:**

Define RNN

Discuss the Applications of RNN

Illustrate how RNN is trained

Discuss Long Short-Term memory(LSTM)

Explain Recursive Neural Tensor Network Theory

Illustrate the working of Neural Network Model

**Topics:**

Intro to RNN Model

Application use cases of RNN

Modelling sequences

Training RNNs with Backpropagation

Long Short-Term memory (LSTM)

Recursive Neural Tensor Network Theory

Recurrent Neural Network Model

**Restricted Boltzmann Machine(RBM) and Autoencoders**

**Objectives:**

**At the end of this Module, you should be able to:**

Define RBM

Discuss the Applications of RBM

Illustrate Collaborative Filtering using RBM

Define Autoencoders

Explain Deep Belief Networks

**Topics:**

Restricted Boltzmann Machine

Applications of RBM

Collaborative Filtering with RBM

Introduction to Autoencoders

Autoencoders applications

Understanding Autoencoders

Variational Autoencoders

Deep Belief Network

This course does not have any sections.