Artificial Intelligence with TensorFlow Overview :
Deep learning is one of the newest technological advances in the fields of artificial intelligence and machine learning. This Deep Learning with TensorFlow course is designed to help you master deep learning techniques and enables you to build deep learning models using the Keras and TensorFlow frameworks. These frameworks are used in deep neural networks and machine learning research, which in turn contributes to the development and implementation of artificial neural networks.
Session 1 : Review of Machine Learning with Python
This module helps you to understand the basics of Python and Machine Learning which is required for this course.
● Linear Regression
● Logistic Regression
● Implementing a Linear Regression model for predicting house prices from
● Implementing a Logistic Regression model for classifying Customers
based on a Automobile purchase dataset
Session 2 : Introduction to Artificial Neural Network with TensorFlow
In this module, you will get an introduction to Deep Learning and understand how Deep Learning solves problems which Machine Learning cannot. Understand the fundamentals of Machine Learning and relevant topics of Linear Algebra and Statistics.
● Deep Learning: A revolution in Artificial Intelligence
● Limitations of Machine Learning
● What is Deep Learning?
● Advantage of Deep Learning over Machine learning
● 3 Reasons to go for Deep Learning
● Real-Life use cases of Deep Learning
● How Deep Learning Works?
● Activation Functions
● Illustrate 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
● Building a single perceptron for classification on SONAR dataset
Session 3 : Deep dive into Neural Networks with TensorFlow
In this module, you will understand the backpropagation algorithm which is used for training Deep Networks. You will know how Deep Learning uses neural networks and backpropagation to solve the problems which Machine Learning cannot. You will understand how it works, its various data types & functionalities.You will learn to create an image classification model.
● 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
● 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
● Building a multi-layered perceptron for classification of Hand-written digits
● Building a multi-layered perceptron for classification on SONAR dataset
Session 4 : Custom Models and Training and Data Processing With TensorFlow
In this module we will be learning about TensorFlow’s lower-level Python API. Till now we have worked with high-level API, tf.keras, but it already got us pretty far.But now it’s time to dive deeper into TensorFlow and take a look at its lower-level Python API. This will be useful when you need extra control to write custom loss functions, custom metrics, layers, models, initializers, regularizers, weight constraints, and more
● A Quick Tour of TensorFlow
● Using TensorFlow like NumPy
● Customizing Models and Training Algorithms
● TensorFlow Functions and Graphs
● The Data API
● The TFRecord Format
● Preprocessing the Input Features
● TF Transform
● The TensorFlow Datasets (TFDS) Project
Session 5 : Deep Computer Vision Using Convolutional Neural Networks
In this module, you will understand convolutional neural networks and its applications. You will understand the working of CNN, and create a CNN model to solve a problem.
● Introduction to CNNs
● CNNs Application
● Architecture of a CNN
● Convolution and Pooling layers in a CNN
● Understanding and Visualizing a CNN
● Building a convolutional neural network for image classification. The
model should predict the difference between 10 categories of images.
Session 6: Recurrent Neural Networks
In this module, you will understand Recurrent Neural Networks and its applications. You will understand the working of RNN, how LSTM are used in RNN, what is Recursive Neural Tensor Network Theory, and finally you will learn to create a RNN model to solve a problem.
● Introduction 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
● Building a recurrent neural network for SPAM prediction.
Session 7 : Restricted Boltzmann Machine (RBM) and Autoencoders
In this module, you will understand RBM & Autoencoders along with their applications. You will understand the working of RBM & Autoencoders, illustrate Collaborative Filtering using RBM and understand what are Deep Belief Networks.
● Restricted Boltzmann Machine
● Applications of RBM
● Collaborative Filtering with RBM
● Introduction to Autoencoders
● Autoencoders applications
● Understanding Autoencoders
● Building a Autoencoder model for classification of handwritten images
extracted from the MNIST Dataset
Session 8 : Reinforcement Learning
In this module, we will first explain what Reinforcement Learning is and what it’s good at, then present two of the most important techniques in Deep Reinforcement Learning: policy gradients and deep Q-networks (DQNs), including a discussion of Markov decision processes (MDPs). We will use these techniques to train models to balance a pole on a moving cart; then I’ll introduce the TF-Agents library, which uses state-of-the-art algorithms that greatly simplify building powerful RL systems, and we will use the library to train an agent to play Breakout, the famous Atari game.
● Learning to Optimize Rewards
● Policy Search
● Introduction to OpenAI Gym
● Neural Network Policies
● Evaluating Actions: The Credit Assignment Problem
● Policy Gradients
● Markov Decision Processes
● Temporal Difference Learning
● Implementing Deep Q-Learning
● Deep Q-Learning Variants
● The TF-Agents Library
● Overview of Some Popular RL Algorithms
● Train an agent to play Breakout, the famous Atari game
Session 9 : Training and Deploying TF Models at Scale
In this module, you will understand how to deploy deep learning models using TensorFlow Serving.
● Serving a TensorFlow Model
● Deploying a Model to a Mobile or Embedded Device
● Using GPUs to speed up Computations
● Training Models across multiple devices
● Creating a Prediction AI service on GCP AI Platform
Session 10 : Hands-On Project
In this module, you should learn how to approach and implement a Deep Learning project end to end, the instructor from the industry will share his experience and insights from the industry to help you kickstart your career in this domain. At last we will be having a QA and doubt clearing session for the students
● How to approach a project?
● Hands-On project implementation
● What Industry expects?
● Industry insights for the Machine Learning domain
● QA and Doubt Clearing Session
● TF-Object Detection
● Image Segmentation
● Object Tracking
● Image Classification
Basic programming knowledge in Python
Concepts about Machine Learning
Duration & Timings :
Duration – 30 Hours.
Training Type: Instructor Led Live Interactive Sessions.
Weekend Session – Sat & Sun 9:30 AM to 12:30 PM (EST) – 5 Weeks. December 11, 2021.
Weekday Session – Mon – Thu 8:30 PM to 10:30 PM (EST) – 4 Weeks. January 10, 2022.