Novice to pro in Deep Learning with Hands-on Real-World Projects
About This Video
In Detail
Deep learning is an artificial intelligence function that mimics the inner workings of the human brain in processing data and creating …
Novice to pro in Deep Learning with Hands-on Real-World Projects
About This Video
In Detail
Deep learning is an artificial intelligence function that mimics the inner workings of the human brain in processing data and creating patterns for use in decision making. Deep learning is a subset of machine learning in artificial intelligence (AI) that has networks of interconnected nodes capable of un-supervised learning from data that is unstructured or unlabelled training data. It also enables representation of data in form of abstract features and classifies them into sub-classes which may be too complex for traditional machine learning models.
One of the most common AI techniques used for processing big data is machine learning, a self-adaptive algorithm that gets increasingly better analysis and patterns with experience or with newly added data. As more and more sources of data-generation are coming into picture, the number of file formats is increasing as well. Now, designing one model to merge data from these many sources and extract meaningful insights is not possible with traditional hand-coded programs. While traditional programs build analysis with data in a linear way, the hierarchical function of deep learning systems enables machines to process data with a non-linear approach. While this may sound daunting, Deep Learning algorithms handle such tasks with ease. The scope of implementation in various sectors is just limitless.
Chapter 1 : Introduction
Introduction 00:09:13
History of Deep learning 00:15:39
Perceptrons 00:07:18
Multi-Level Perceptrons 00:13:07
Neural Network Playground 00:10:27
Representations 00:21:32
Training Neural Network - Part 1 00:21:33
Training Neural Network - Part 2 00:07:00
Training Neural Network - Part 3 00:33:02
Activation Functions 00:13:29
Chapter 2 : Artificial Neural Networks-Introduction
Introduction 00:07:29
Deep Learning 00:09:08
Understanding Human Brain 00:09:13
Perceptron 00:11:18
Perceptron for Classifiers 00:08:22
Perceptron in Depth 00:08:18
Homogeneous Co-ordinate 00:07:01
Example for Perceptron 00:09:37
Multi Classifier 00:09:52
Neural Networks 00:10:47
Input Layer 00:12:40
Output Layer 00:03:07
Sigmoid function 00:06:05
Understanding MNIST 00:04:08
Assumptions in Neural Networks 00:07:26
Training in Neural Networks 00:06:40
Understanding Notations 00:19:31
Activation Functions 00:11:23
Chapter 3 : ANN - Feed Forward Network
Introduction 00:14:13
Online Offline Mode 00:08:52
Bidirectional RNN 00:05:58
Understanding Dimensions 00:05:26
Pseudocode 00:11:28
Pseudocode for Batch 00:09:24
Vectorised Methods 00:10:10
Chapter 4 : Back Propagation
Introduction 00:10:20
Introducing Loss Function 00:14:20
Back Propagation Training - Part 1 00:10:49
Back Propagation Training - Part 2 00:09:37
Back Propagation Training - Part 3 00:04:56
Back Propagation Training - Part 4 00:08:46
Back Propagation Training - Part 5 00:10:09
Sigmoid Function 00:07:40
Back Propagation Training - Part 6 00:07:46
Back Propagation Training - Part 7 00:06:29
Back Propagation Training - Part 8 00:08:02
Back Propagation Training - Part 9 00:10:20
Back Propagation Training - Part 10 00:07:22
Pseudocode 00:03:43
SGD 00:10:31
Finding Global Minima 00:02:38
Training for Batches 00:07:08
Chapter 5 : Regularisation
Introduction to Regularisation 00:14:32
Dropouts Part 1 00:08:37
Dropouts Part 2 00:05:09
Batch Normalisation - Part 1 00:04:06
Batch Normalisation - Part 2 00:02:30
Batch Normalisation - Part 3 00:05:32
Introducing TensorFlow 00:10:12
Introducing Keras 00:11:46
Chapter 6 : Convolution Neural Networks
Introduction 00:12:55
Applications for CNN 00:07:29
Idea behind CNN - Part 1 00:05:07
Idea behind CNN - Part 2 00:08:28
Images 00:21:00
Video 00:07:36
Convolution - Part 1 00:08:49
Convolution - Part 2 00:08:40
Stride and Padding 00:06:57
Padding 00:04:28
Formulas 00:06:12
Weight and Bias 00:15:24
Feature Map 00:12:02
Pooling 00:08:46
Combining Network 00:05:56
Chapter 7 : CNN-Keras
Introduction 00:02:52
VGG16 (Visual Geometry Group) 00:16:15
Practical on CNN: Case Study - Part 1 00:04:15
Practical on CNN: Case Study - Part 2 00:08:00
Practical on CNN: Case Study - Part 3 00:09:47
Practical on CNN: Case Study - Part 4 00:04:53
Practical on CNN: Case Study - Part 5 00:03:00
Chapter 8 : CNN-Transfer Learning
Introduction 00:09:00
AlexNet 00:11:48
GoogleNet 00:04:23
ResNet - Part 1 00:07:31
ResNet - Part 2 00:07:09
Transfer Learning - Part 1 00:04:09
Transfer Learning - Part 2 00:04:05
Transfer Learning - Part 3 00:04:11
Transfer Learning - Part 4 00:03:26
Transfer Learning - Part 5 00:03:56
Transfer Learning - Part 6 00:03:13
Case Study - Part 1 00:14:27
Case Study - Part 2 00:06:14
Case Study - Part 3 00:03:24
Analysis - Part 1 00:08:45
Analysis - Part 2 00:01:56
Chapter 9 : CNN-Industry Live Project: Playing With Real World Natural Images
Introduction 00:06:42
Working with Flower Images: Case Study - Part 1 00:04:07
Working with Flower Images: Case Study - Part 2 00:09:06
Working with Flower Images: Case Study - Part 3 00:05:51
Working with Flower Images: Case Study - Part 4 00:06:21
Working with Flower Images: Case Study - Part 5 00:06:59
Working with Flower Images: Case Study - Part 6 00:06:08
Working with Flower Images: Case Study - Part 7 00:02:51
Working with Flower Images: Case Study - Part 8 00:14:04
Working with Flower Images: Case Study - Part 9 00:05:48
Working with Flower Images: Case Study - Part 10 00:05:07
Working with Flower Images: Case Study - Part 11 00:06:46
Working with Flower Images: Case Study - Part 12 00:12:45
Working with Flower Images: Case Study - Part 13 00:02:22
Working with Flower Images: Case Study - Part 14 00:07:42
Chapter 10 : CNN-Industry Live Project: Find Medical Abnormalities and Save Life
Introduction 00:03:13
Working with X-Ray images: Case Study - Part 1 00:02:21
Working with X-Ray images: Case Study - Part 2 00:02:32
Working with X-Ray images: Case Study - Part 3 00:04:33
Working with X-Ray images: Case Study - Part 4 00:04:28
Working with X-Ray images: Case Study - Part 5 00:07:17
Working with X-Ray images: Case Study - Part 6 00:05:25
Chapter 11 : Recurrent Neural Networks: Introduction
Introduction to RNN 00:08:00
RNN - Part 1 00:05:09
RNN Part 2 00:03:36
RNN Formula 00:17:00
Architecture 00:11:03
Batch data 00:04:47
Simplified Notations 00:14:03
Types of RNN - Part 1 00:04:08
Types of RNN - Part 2 00:06:47
Training RNN 00:06:05
One-to-Many 00:08:29
Vanishing Gradient 00:10:58
Chapter 12 : Recurrent Neural Networks: LSTM
Introduction 00:02:57
Online Offline Mode 00:06:27
Bidirectional RNN 00:08:46
LSTM - Part 1 00:05:04
LSTM - Part 2 00:03:21
LSTM - Part 3 00:02:05
LSTM - Part 4 00:07:55
LSTM - Part 5 00:06:22
LSTM Equation 00:02:49
Gated Recurrent Network (GRU) 00:11:39
Chapter 13 : Recurrent Neutral Networks: Part-Of-Speech Tagger
Part-Of-Speech Tagger case-study (Part-1) 00:08:23
Part-Of-Speech Tagger case- study (Part-2) 00:08:22
Part-Of-Speech Tagger case- study (Part-3) 00:04:35
Part-Of-Speech Tagger case- study (Part-4) 00:09:32
Part-Of-Speech Tagger case- study (Part-5) 00:09:35
Part-Of-Speech Tagger case- study (Part-6) 00:06:42
Part-Of-Speech Tagger case- study (Part-7) 00:05:11
Part-Of-Speech Tagger case- study (Part-8) 00:07:06
Part-Of-Speech Tagger case- study (Part-9) 00:02:17
Chapter 14 : Text generation using RNN
Text Generation: Code generator case- study (Part-1) 00:14:11
Text Generation: Code generator case- study (Part-2) 00:06:52
Text Generation: Code generator case- study (Part-3) 00:02:42
Text Generation: Code generator case- study (Part-4) 00:04:15