AI Engineer : Deep Learning Specialization

498 Learners

Differentiate deep learning from machine learning. Explore various neural network types. Excel at forward and backward propagation in deep neural networks. Introduce modeling and performance enhancement in deep learning. Understand hyperparameter tuning and model interpretability. Learn dropout and early stopping implementation. Master CNNs, object detection, and RNN fundamentals. Grasp PyTorch basics and neural network creation.

Course Overview

Course Overview to be entered here

Course Curriculum

Course Content

AI Technical Engineer : Deep Learning Specialization
Preview
- Lesson 01: Course Introduction
  04:55Preview
  - 1.01 Course Introduction
    02:50
  - 1.02 What You Will Learn
    02:05
- Lesson 02: Introduction to Deep Learning
  34:53Preview
  - 2.01 Introduction
    01:10
  - 2.02 Introduction to Deep Learning
    02:36
  - 2.03 Brief History of AI
    03:20
  - 2.04 Motivation for Deep Learning
    06:01
  - 2.05 Difference Between Deep learning and Machine Learning
    05:00
  - 2.06 Deep Learning Successes in the Last Decade
    03:32
  - 2.07 Applications of Deep learning
    02:12
  - 2.08 Challenges of Deep Learning
    02:08
  - 2.09 Deep Learning Frameworks
    02:12
  - 2.10 Fullcycle of a Deep Learning Project
    02:54
  - 2.11 Neural Networks and Types of Neural Network
    02:49
  - 2.12 Recap
    00:59
- Lesson 03: Perceptron
  18:27Preview
  - 3.01 Introduction
    00:48
  - 3.02 What is a Perceptron
    02:24
  - 3.03 Forward Propagation in Perceptron
    02:40
  - 3.04 Role of Activation Functions
    03:08
  - 3.05 Backward Propagation in Perceptron
    02:48
  - 3.06 Gradient Descent Algorithm
    02:11
  - 3.07 Limitations of Perceptron
    01:01
  - 3.08 Recap
    00:50
  - 3.09 Spotlight Introduction to Artificial Intelligence
    02:37
- Lesson 04: Deep Neural Networks(DNN)
  21:57Preview
  - 4.01 Introduction
    00:51
  - 4.02 What is deep neural network (DNN) Why it is useful
    02:20
  - 4.03 Loss Functions: Part 1
    02:20
  - 4.04 Loss Functions: Part 2
    02:21
  - 4.05 Forward Propagation in DNN
    02:25
  - 4.06 Backward Propagation in DNN
    02:12
  - 4.07 Introduction to TensorFlow
    02:29
  - 4.08 Training DNN Using Tensorflow
    02:31
  - 4.09 Introduction to TensorFlow Playground
    03:48
  - 4.10 Recap
    00:40
- Lesson 05: TensorFlow2
  20:24Preview
  - 5.01 Introduction
    00:48
  - 5.02 Overview of TensorFlow
    01:54
  - 5.03 Installation of TensorFLow2
    04:34
  - 5.04 Introduction to Tensors
    04:24
  - 5.05 Sequential APIs in TensorFlow
    02:53
  - 5.06 Functional APIs in TensorFlow
    02:53
  - 5.07 Keras an Introduction
    02:06
  - 5.08 Recap
    00:52
- Lesson 06: Model Optimization and Performance Improvement
  01:57:31Preview
  - 6.01 Introduction
    01:09
  - 6.02 Introduction to Optimization Algorithms
    01:48
  - 6.03 Introduction to SGD
    02:05
  - 6.04 Implementation of SGD
    06:31
  - 6.05 Introduction to Momentum
    01:24
  - 6.06 Implementation of Momentum
    09:39
  - 6.07 Introduction to Adagrad
    02:39
  - 6.08 Implementation of Adagrad
    10:22
  - 6.08 Introduction to Adadelta
    02:35
  - 6.09 Implementation of Adadelta
    10:15
  - 6.10 Introduction to RMSProp
    01:49
  - 6.11 Implementation of RMSprop
    11:15
  - 6.12 Introduction to Adam
    02:43
  - 6.13 Implementation of Adam
    09:36
  - 6.14 What is Batch Normalization
    02:04
  - 6.15 Batch Normalization Implementation
    02:07
  - 6.16 Exploding and Vanishing Gradients
    02:33
  - 6.17 Introduction to Hyperparameter Tuning
    02:08
  - 6.19 Implementation of Hyperparameter Tuning
    07:33
  - 6.18 Model Interpretability
    03:04
  - 6.19 Dropout and Early Stopping
    02:44
  - 6.20 Implementation of Dropout
    11:10
  - 6.21 Implementation of Early Stopping
    06:23
  - 6.22 Recap
    00:53
  - 6.23 Spotlight Introduction to Neural Networks and Computer Vision
    03:02
- Lesson 07: Convolutional Neural Networks (CNN)
  45:33Preview
  - 7.01 Introduction
    00:52
  - 7.02 Getting Started with Image Data
    03:22
  - 7.03 What is a Convolutional Neural Networks (CNN)
    03:19
  - 7.04 CNN Architecture
    02:35
  - 7.05 ResNet 50
    02:55
  - 7.06 Filters in CNN
    01:41
  - 7.07 Working of CNN
    02:52
  - 7.08 Pooling in CNN
    02:11
  - 7.09 Image Classification Using CNN
    17:44
  - 7.10 Introduction to Tensorboard
    07:13
  - 7.11 Recap
    00:49
- Lesson 08: Transfer Learning
  07:48
  - 8.01 Introduction
    00:40
  - 8.02 Introduction to Transfer Learning
    02:09
  - 8.03 How to Select Pre Trained Models
    02:38
  - 8.04 Advantages of Transfer Learning
    01:51
  - 8.05 Recap
    00:30
- Lesson 09: Object Detection
  36:23Preview
  - 9.01 Introduction
    00:56
  - 9.02 Introduction to Object Detection
    02:25
  - 9.03 Object Detection for Multiple Objects
    02:26
  - 9.04 High Level Overview of YOLO v3 Algorithm
    02:54
  - 9.05 Dataset Preparation for YOLO v3
    01:57
  - 9.06 Object Detection with YOLO v3: Part A
    07:11
  - 9.07 Object Detection with YOLO v3: Part B
    06:33
  - 9.08 Introduction to TF Lite
    02:28
  - 9.09 Converting TF Model into TF Lite Model
    05:37
  - 9.10 Recap
    01:00
  - 9.11 Spotlight Advanced Computer Vision
    02:56
- Lesson 10: Recurrent Neural Networks (RNN)
  15:52Preview
  - 10.01 Introduction
    00:56
  - 10.02 What is Sequence Modeling
    02:09
  - 10.03 Introduction to Recurrent Neural Networks (RNN)
    02:43
  - 10.04 Architecture of RNN
    02:14
  - 10.05 Forward and Back Propagation in RNN
    02:15
  - 10.06 Introduction to Hybrid Modeling
    01:42
  - 10.07 Architecture of a CNN and RNN hybrid model
    03:13
  - 10.08 Recap
    00:40
- Lesson 11: Transformer Models for NLP
  08:42Preview
  - 11.01 Introduction
    00:46
  - 11.02 Overview of Transformer Models
    01:41
  - 11.03 Architecture of the Transformer Model
    03:21
  - 11.04 Introduction to BERT Model (BERT Architecture and use cases)
    02:20
  - 11.05 Recap
    00:34
- Lesson 12: Getting Started with Autoencoders
  17:00Preview
  - 12.01 Introduction
    00:39
  - 12.02 Introduction to Unsupervised Deep Learning
    01:47
  - 12.03 What are Autoencoders
    01:36
  - 12.04 Architecture of Autoencoders
    01:32
  - 12.05 Use Cases of Autoencoders
    01:06
  - 12.06 Training Autoencoders
    09:58
  - 12.07 Recap
    00:22
- Lesson 13: PyTorch
  22:01Preview
  - 13.01 Introduction
    00:48
  - 13.02 Introduction to PyTorch
    02:25
  - 13.03 Getting Started with PyTorch
    07:23
  - 13.04 Creating a Neural Network in PyTorch
    07:42
  - 13.05 Recap
    00:34
  - 13.06 Spotlight Advanced Deep Learning
    03:09

Why Join this Program

Develop skills for real career growthCutting-edge curriculum designed in guidance with industry and academia to develop job-ready skills
Learn from experts active in their field, not out-of-touch trainersLeading practitioners who bring current best practices and case studies to sessions that fit into your work schedule.
Learn by working on real-world problemsCapstone projects involving real world data sets with virtual labs for hands-on learning
Structured guidance ensuring learning never stops24x7 Learning support from mentors and a community of like-minded peers to resolve any conceptual doubts

Acknowledgement
PMP, PMI, PMBOK, CAPM, PgMP, PfMP, ACP, PBA, RMP, SP, OPM3 and the PMI ATP seal are the registered marks of the Project Management Institute, Inc.

AI Engineer : Deep Learning Specialization

Course Overview

Course Curriculum

Course Content

AI Technical Engineer : Deep Learning Specialization

Lesson 01: Course Introduction

1.01 Course Introduction

1.02 What You Will Learn

Lesson 02: Introduction to Deep Learning

2.01 Introduction

2.02 Introduction to Deep Learning

2.03 Brief History of AI

2.04 Motivation for Deep Learning

2.05 Difference Between Deep learning and Machine Learning

2.06 Deep Learning Successes in the Last Decade

2.07 Applications of Deep learning

2.08 Challenges of Deep Learning

2.09 Deep Learning Frameworks

2.10 Fullcycle of a Deep Learning Project

2.11 Neural Networks and Types of Neural Network

2.12 Recap

Lesson 03: Perceptron

3.01 Introduction

3.02 What is a Perceptron

3.03 Forward Propagation in Perceptron

3.04 Role of Activation Functions

3.05 Backward Propagation in Perceptron

3.06 Gradient Descent Algorithm

3.07 Limitations of Perceptron

3.08 Recap

3.09 Spotlight Introduction to Artificial Intelligence

Lesson 04: Deep Neural Networks(DNN)

4.01 Introduction

4.02 What is deep neural network (DNN) Why it is useful

4.03 Loss Functions: Part 1

4.04 Loss Functions: Part 2

4.05 Forward Propagation in DNN

4.06 Backward Propagation in DNN

4.07 Introduction to TensorFlow

4.08 Training DNN Using Tensorflow

4.09 Introduction to TensorFlow Playground

4.10 Recap

Lesson 05: TensorFlow2

5.01 Introduction

5.02 Overview of TensorFlow

5.03 Installation of TensorFLow2

5.04 Introduction to Tensors

5.05 Sequential APIs in TensorFlow

5.06 Functional APIs in TensorFlow

5.07 Keras an Introduction

5.08 Recap

Lesson 06: Model Optimization and Performance Improvement

6.01 Introduction

6.02 Introduction to Optimization Algorithms

6.03 Introduction to SGD

6.04 Implementation of SGD

6.05 Introduction to Momentum

6.06 Implementation of Momentum

6.07 Introduction to Adagrad

6.08 Implementation of Adagrad

6.08 Introduction to Adadelta

6.09 Implementation of Adadelta

6.10 Introduction to RMSProp

6.11 Implementation of RMSprop

6.12 Introduction to Adam

6.13 Implementation of Adam

6.14 What is Batch Normalization

6.15 Batch Normalization Implementation

6.16 Exploding and Vanishing Gradients

6.17 Introduction to Hyperparameter Tuning

6.19 Implementation of Hyperparameter Tuning

6.18 Model Interpretability

6.19 Dropout and Early Stopping

6.20 Implementation of Dropout

6.21 Implementation of Early Stopping

6.22 Recap

6.23 Spotlight Introduction to Neural Networks and Computer Vision

Lesson 07: Convolutional Neural Networks (CNN)

7.01 Introduction

7.02 Getting Started with Image Data