AI & Deep Learning with TensorFlow
Overview
Deep Learning in TensorFlow with Python Certification Training is curated by industry professionals as per the industry requirements & demands. You will master the concepts such as SoftMax function, Autoencoder Neural Networks, Restricted Boltzmann Machine (RBM) and work with libraries like Keras & TFLearn. The course has been specially curated by industry experts with real-time case studies.
Section 1Introduction to Deep Learning
Lecture 1Deep Learning: A revolution in Artificial Intelligence
Lecture 2 Limitations of Machine Learning
Lecture 3 What is Deep Learning?
Lecture 4Advantage of Deep Learning over Machine learning
Lecture 5 3 Reasons to go for Deep Learning
Lecture 6 Real-Life use cases of Deep Learning
Lecture 7 Review of Machine Learning: Regression, Classification, Clustering, Reinforcement Learning, Underfitting and Overfitting, Optimization
Section 2Understanding Neural Networks with TensorFlow
Lecture 8 How Deep Learning Works?
Lecture 9 Activation Functions
Lecture 10 Illustrate Perceptron
Lecture 11 Training a Perceptron
Lecture 12 Important Parameters of Perceptron
Lecture 13 What is TensorFlow?
Lecture 14 TensorFlow code-basics
Lecture 15 Graph Visualization
Lecture 16 Constants, Placeholders, Variables
Lecture 17 Creating a Model
Lecture 18 Step by Step – Use-Case Implementation
Section 3Deep dive into Neural Networks with TensorFlow
Lecture 19 Understand limitations of a Single Perceptron
Lecture 20 Understand Neural Networks in Detail
Lecture 21 Illustrate Multi-Layer Perceptron
Lecture 22 Backpropagation – Learning Algorithm
Lecture 23 Understand Backpropagation – Using Neural Network Example
Lecture 24 MLP Digit-Classifier using TensorFlow
Lecture 25 TensorBoard
Section 4Master Deep Networks
Lecture 26 Why Deep Networks
Lecture 27Why Deep Networks give better accuracy?
Lecture 28 Use-Case Implementation on SONAR dataset
Lecture 29 Understand How Deep Network Works?
Lecture 30 How Backpropagation Works?
Lecture 31 Illustrate Forward pass, Backward pass
Lecture 32 Different variants of Gradient Descent
Lecture 33 Types of Deep Networks
Section 5Convolutional Neural Networks (CNN)
Lecture 34 Introduction to CNNs
Lecture 35 CNNs Application
Lecture 36 Architecture of a CNN
Lecture 37 Convolution and Pooling layers in a CNN
Lecture 38 Understanding and Visualizing a CNN
Section 6Recurrent Neural Networks (RNN)
Lecture 39 Introduction to RNN Model
Lecture 40 Application use cases of RNN
Lecture 41 Modelling sequences
Lecture 42 Training RNNs with Backpropagation
Lecture 43 Long Short-Term memory (LSTM)
Lecture 44 Recursive Neural Tensor Network Theory
Lecture 45 Recurrent Neural Network Model
Section 7Restricted Boltzmann Machine (RBM) and Autoencoders
Lecture 46 Restricted Boltzmann Machine
Lecture 47 Applications of RBM
Lecture 48 Collaborative Filtering with RBM
Lecture 49 Introduction to Autoencoders
Lecture 50 Autoencoders applications
Lecture 51 Understanding Autoencoders
Section 8Keras API
Lecture 52 Define Keras
Lecture 53 How to compose Models in Keras
Lecture 54 Sequential Composition
Lecture 55 Functional Composition
Lecture 56 Predefined Neural Network Layers
Lecture 57 What is Batch Normalization
Lecture 58 Saving and Loading a model with Keras
Lecture 59 Customizing the Training Process
Lecture 60 Using TensorBoard with Keras
Lecture 61 Use-Case Implementation with Keras
Section 9TFLearn API
Lecture 62 Define TFLearn
Lecture 63 Composing Models in TFLearn
Lecture 64 Sequential Composition
Lecture 65 Functional Composition
Lecture 66 Predefined Neural Network Layers
Lecture 67 What is Batch Normalization
Lecture 68 Saving and Loading a model with TFLearn
Lecture 69 Customizing the Training Process
Lecture 70 Using TensorBoard with TFLearn
Lecture 71 Use-Case Implementation with TFLearn
Section 10In-Class Project
Lecture 72 How to approach a project?
Lecture 73 Hands-On project implementation
Lecture 74 What Industry expects?
Lecture 75 Industry insights for the Machine Learning domain
Lecture 76 QA and Doubt Clearing Session
