Deep Learning Certification Course

1.0 Foundations (5+Hrs)

1.1 Python

1.1.1. Overview of python

1.1.2. Basics of python

1.1.3. Python datastrucutre

1.1.4. Python libraries for AI & ML

1.1.4.1. Numpy – Statistical Analysis

1.1.4.2. Pandas –

1.1.4.3. Matplotlib – Data visualisation

1.1.5. Debugging methodology

1.1.6. Hands on sessions

1.1.7. Milestone project

1.2 Statistics

1.2.1 Probability

1.2.2 Basic statistics

1.2.3 Terminology in statistics

1.2.4 Distributions

1.2.5 Statistical theorems

1.2.5.1. Central Limit theorem

1.2.5.2. Baye’s theorem

1.2.6 Descriptive analysis and descriptive statistics

1.2.7 Inferential analysis and Inferential statistics

1.2.8 Statistical Significance

1.2.9 Hypothesis testing

1.2.10 Bias – Variance trade-off

2.0 Pre-set up (3+Hrs)

2.1. System requirements

2.2. Installations

2.3. Environment setup

3.0 Machine Learning (15+Hrs)

3.1. Introduction to Machine Learning

3.2. Analytics and its types

3.3. Machine Learning and its types

3.4. Algorithms and techniques

4.0 Feature Engineering (4+Hrs)

4.1. Model selection and tuning

4.2. Feature extraction

4.3. Error metrics and evaluation

4.4. Milestone project

5.0 Decision making methodology (6+Hrs)

5.1. Genetic Algorithm

5.2. Linear programming

5.3. Monte Carlo simulations

5.4. Neural networks concepts

6.0 Deep Learning (18+Hrs)

6.1 Introduction to deep learning

6.2 Insights of Neural networks

6.3 Fameworks of Neural networks

6.3.1 Tensorflow

6.3.2 Keras

7.0 Neural Networks (13+Hrs)

7.1 Basics

7.1.1 What is neuron?

7.1.2 What is neural network?

7.1.3 Perceptrons

7.1.4 Hidden Layers

7.1.5 Neuron predictions

7.1.6 Neuron training

7.1.7 Back propogation

7.2 Intermediate

7.2.1 No linear activation function

7.2.2 Back propagation

7.2.3 Vanishing and exploding gradient descent

7.2.4 How to mitigate over fitting?

7.2.5 Pre-trained models

   7.2.6 Transfer learning – Resnet

8.0 Artificial Neural Network – ANN (15+Hrs)

8.1 What is ANN?

8.2 Building an ANN model

8.3 Fine-tuning the model

8.3.1 Evaluating

8.3.2 Defect diagnosing

8.3.3 Improving the model

8.3.4 Tuning the ANN model

8.4 Hands-on project

9.0 Convolution Neural Network – CNN (4+Hrs)

9.1 What is CNN?

9.2 Building a CNN model

9.2.1 CNN – operation

9.2.2 ReLU layer

9.2.3 Pooling

9.2.4 Flattening

9.3 Fine-tuning the model

9.3.1 Evaluating

9.3.2 Defect diagnosing

9.3.3 Improving the model

9.3.4 Tuning the CNN model

9.4 Hands-on project

10.0 Recurrent Neural Network (5+Hrs)

10.1 What is RNN?

10.2 Building a RNN model

10.3 Fine-tuning the model

10.3.1 Evaluating

10.3.2 Defect diagnosing

10.3.3 Improving the model

10.3.4 Tuning the RNN model

10.4 LSTM’s

10.5 Hands-on project

11.0 Reinforcement learning (5+Hrs)

11.1 What is reinforcement learning?

11.2 Markov Decision Process - MDP

11.3 Dynamic programming to solve MDP

11.4 Prediction and reinforcement testing(use case)

11.5 Milestone project

12.0 Computer vision (5+Hrs)

12.1 What is computer vision?

12.2 Importing data(image & video) through different methods

12.3 Image processing

12.3.1 Converting into matrix

12.3.2 Color spaces

12.3.3 Contouring

12.3.4 Filtering

12.3.5 Feature extraction

12.3.6 Sizing and more..

12.4 Image recognition and its applications

12.5 Hands –on Project

13.0 Advanced AI (5+Hrs)

13.1 Advanced Computer vision

13.2 Image recognition in comparison with Basis NN and CNN

13.3 Bi-directional recurrent models

13.4 Object detection and image segmentation

13.5 OpenCV and tensorflow projects

13.6 YOLO, Faster RCNN and SSD models

13.7 Examples with pre-trained models

13.8 Generative Adversial Network – GANs

13.9 Applications of GANs

13.10 Hands-on project on facial recognition and identification

13.11 Hands-on project on Object identification.

14.0 Career Assistance (3+Hrs)

14.1 Resume Building

14.2 Internship

14.3 Interview preparation

14.4 Complete career guidance