Deep Learning with Python and TensorFlow Training
Deep Learning with Python and TensorFlow
=====
—–
* Course Id : DSCI-PYTF
* Duration : 24 Hours
Overview
—–
* This course is designed to provide an introduction to Deep Learning
* It helps you understand how Deep Learning solves problems which Machine Learning cannot
* Participants will understand fundamentals of Machine Learning and relevant topics of Linear Algebra and Statistics
* They are also introduced to Neural Networks and understand how it is trained, parameters used, activation functions
* Participants learn to use algorithms to train Deep Networks
* Get started with TensorFlow
* They will also use APIs built on top of TensorFlow
Training Objectives
—–
All attendees will learn:
* Review of Machine Learning fundamentals
* Regression, classification, clustering algorithms, and SciPy
* How Deep Learning uses neural network
* algorithms to solve the problems that Machine Learning cannot
* How to get started with the TensorFlow framework
* How TF works, its various data types & functionalities
* Use Keras API and TFLearn API
Pre-Requisites
—–
Basic knowledge on:
* Basic programming skills in Python
* Awareness of machine learning
Course Structure
—–
* We provide more focus on hands-on in our technical courses (typically 80% hands-on/20% theory)
* Students get the capability to apply the material they learn to real-world problems
Materials Provided
—–
* All participants receive
* PDF of slides
* PDF of handson
* Access to instance with lab environment
Software Requirements
—–
Any of the following
* Any current internet browser
* vnc client
* rdp client
Hardware Requirements
—–
* Processor: 1.2 GHz+
* RAM: 512 MB+
* Disk space: 1 GB+
* Network Connection with low latency (<250ms) to Internet
## Daywise Deep Learning with Python and TensorFlow Course Outline
—–
## Day 1
—–
* Unit 1 : Introduction to Machine Learning
* Unit 2 : Introduction to Deep Learning
* Unit 3 : Understanding Neural Networks with TensorFlow
## Day 2
—–
* Unit 4 : Deep dive into Neural Networks with TensorFlow
* Unit 5 : Master Deep Networks
* Unit 6 : Understand CNN and RNN
## Day 3
—–
* Unit 8 : Keras API
* Unit 8 : TFLearn API
## Detailed Deep Learning with Python and TensorFlow Outline
Unit 1 : Introduction to Machine Learning
* Introduction to Machine Learning
* Python for Machine Learning
* Supervised vs Unsupervised ML
* Applications of Machine Learning
* Advantages of using Python libraries for ML
Unit 2 : Introduction to Deep Learning
* Deep Learning: A revolution in Artificial Intelligence
* Limitations of Machine Learning
* What is Deep Learning?
* Advantages of Deep Learning over Machine learning
* Three Reasons to go for Deep Learning
* Real-Life use cases of Deep Learning
* Review of Machine Learning
* Regression
* Classification
* Clustering
* Reinforcement Learning
* Underfitting and Overfitting
* Optimization
Unit 3 : Understanding Neural Networks with TensorFlow
* How Deep Learning Works?
* Activation Functions
* What is a Perceptron
* Training a Perceptron
* Important Parameters of Perceptron
* What is TensorFlow?
* TensorFlow code-basics
* Graph Visualization
* Constants, Placeholders, Variables
* Creating a Model
* Step by Step – Use-Case Implementation
Unit 4 : Deep dive into Neural Networks with TensorFlow
* Understand limitations of a Single Perceptron
* Understand Neural Networks in Detail
* Illustrate Multi-Layer Perceptron
* Backpropagation – Learning Algorithm
* Understand Backpropagation – Using Neural Network Example
* MLP Digit-Classifier using TensorFlow
* TensorBoard
Unit 5 : Master Deep Networks
* Why Deep Networks
* Why Deep Networks give better accuracy?
* Use-Case Implementation on SONAR dataset
* Understand How Deep Network Works?
* How Backpropagation Works?
* Illustrate Forward pass, Backward pass
* Different variants of Gradient Descent
* Types of Deep Networks
Unit 6 : Understand CNN and RNN
* Introduction to CNNs
* Applying CNNs
* Introduction to RNNs
* Applying RNNs
Unit 7 : Keras API
* Define Keras
* How to compose Models in Keras
* Sequential Composition
* Functional Composition
* Predefined Neural Network Layers
* What is Batch Normalization
* Saving and Loading a model with Keras
* Customizing the Training Process
* Using TensorBoard with Keras
* Use-Case Implementation with Keras
Unit 8 : TFLearn API
* Define TFLearn
* Composing Models in TFLearn
* Sequential Composition
* Functional Composition
* Predefined Neural Network Layers
* What is Batch Normalization
* Saving and Loading a model with TFLearn
* Customizing the Training Process
* Using TensorBoard with TFLearn
* Use-Case Implementation with TFLearn
