course content: -

Introduction of Artificial Intelligence

·         Introduction of Artificial Intelligence

·         Terminologies of Artificial Intelligence

·         Components of Artificial Intelligence – ML & DL

·         Difference between AI, ML, Deep Learning

·         Introduction to Machine Learning

·         History and Evolution of AI

·         Find out where AI is applied in Technology and Science.

·         Difference between Traditional Programming and ML Programming

Steps of AI/ML Implementations

·         Types of Machine Learning

·         Labelled Data and Unlabeled Data

·         Concept of Supervised Machine Learning

·         Concept of Unsupervised Machine Learning

·         Steps of Machine Learning

·         Concept of Collecting the historic training Data for ML

·         Concept of Preprocess data for Machine Learning

·         Concept of Train the ML model

·         Concept of Test the ML Algorithm

·         Concept of using the ML Algorithm

Data Collection for Machine Learning

·         Introduction

·         Types of Data collection- Offline Data and Online Data

·         Practical implementations of Reading the offline dataset using Numpy

·         Practical implementations of Reading the online dataset using Numpy

·         Practical implementations of Reading the offline dataset using Pandas

·         Practical implementations of Reading the online iris dataset using Pandas

Concept of Supervise & Unsupervised Machine Learning

·         Introduction

·         Types of Machine Learning

·         Labelled Data and Unlabeled Data

·         Concept of Supervised Machine Learning

·         Concept of Unsupervised Machine Learning

·         Regression and Classification

·         Linear Regression and Logistic Regression

Data Visualization for Machine Learning using Matplotlib

·         Introduction

·         Concept of Univariate plots

·         Univariate Histogram Plots.

·         Univariate Density Plots.

·         Univariate Box and Whisker Plots.

·         Concept of Multivariate plots

·         Correlation Matrix Plot

·         Scatter Matrix Plot

Practical implementation of Supervised ML Algorithm

·         Introduction

·         Implementation Foundation of Supervised Machine Learning Algorithms

·         Regression and Classification

·         Linear Regression and Logistic Regression

·         Practical implementations of Supervised ML Algorithms- Linear Regression

·         Practical implementations of Supervised ML Algorithms- Logistic Regression

·         Concept of Sigmoid Function

·         k-NN Algorithm

·         Naive Bayes Classifiers

·         Decision trees etc.

Practical implementation of Unsupervised Machine Learning 

·         Introduction

·         Concepts and Steps of Unsupervised Machine Learning Algorithm 

·         Concept of Clustering,

·         Practical implementations of Machine Learning Unsupervised Algorithms

·         K-Means Clustering.

Prepare Data for ML using Data Transformation Methods

·         Introduction

·         Need for Data Pre-processing

·         Data Transforms Steps

·         Types of Data Transformation Methods

·         Rescale Data

·         Standardize Data

·         Normalize Data

·         Binarize Data

Feature Selection for Machine Learning

·         Introduction

·         Feature Selection

·         Univariate Feature Selection

·         Recursive Feature Elimination

·         Principal Component Analysis

·         Feature Selection based on Importance.

Data Resampling Methods for Evaluation of ML Models

·         Introduction

·         Evaluate Machine Learning Algorithms

·         Split into Train and Test Sets

·         K-fold Cross Validation

·         Leave One Out Cross Validation

·         Repeated Random Test-Train Splits

·         What Techniques to Use When

Machine Learning Algorithm Performance Evaluation Metrics

·         Introduction

·         Algorithm Evaluation Metrics

·         Logistic Regression Algorithm Performance Evaluation Metrics

·         Classification Accuracy (Default).

·         Logarithmic Loss.

·         Area Under ROC Curve (AUC).

·         Confusion Matrix.

·         Classification Report.

·         Linear Regression Algorithm Performance Evaluation Metrics

·         Mean Absolute Error.

·         Mean Squared Error.

·         R2 Error

Spot-Check Machine Learning Algorithms

·         Concept of Algorithm Spot-Checking

·         Algorithms Overview

·         Linear Machine Learning Algorithms Spot-check

·         Nonlinear Machine Learning Algorithms Spot-check

Introduction to Deep Learning

·         A revolution in Artificial Intelligence

·         Limitations of Machine Learning

·         What is Deep Learning?

·         Advantage of Deep Learning over Machine learning

Introduction to Neural Networks

·         How Deep Learning Works?

·         Introduction to Neural Networks

·         Neural Network Architecture

·         The Neuron

·         Training a Perceptron

·         Concept of Gradient Descent

·         Stochastic Gradient Descent (SDG)

·         Activation Functions

·         Neural Network Layers

Deep dive into ANN with Tensor Flow

·         Understand limitations of a Single Perceptron

·         Deepening the network

·         Tensor Flow code-basics

·         Tensor flow data types

·         CPU vs GPU vs TPU

·         Tensor flow methods

·         Overfitting and Regularization

·         Debugging Neural Networks

·         Visualizing NN using Tensor Flow

·         The MNIST Dataset

·         Coding MNIST NN

·         Linear Regression example revisited.

·         Generalization, Overfitting, Under fitting

Computer Vision 

·         Introduction to image processing and computer vision

·         Convolutional features for visual recognition

·         Object detection

·         Image classification

Introduction of Convolutional Neural Networks (CNN)

·         Introduction

·         Images and Pixels

·         How humans recognize images

·         Convolutional Neural Networks

Architecture of Convolutional Neural Networks (CNN)

·         ConvNet Architecture

·         Strides and Zero Padding

·         Max Pooling and ReLU activations

·         Dropout

·         Coding Deep ConvNets demo

Keras API

·         Keras API

·         How to compose Models using Keras

·         Sequential Composition

·         Neural Network Layers with Keras & Tensor Flow

Conclusion and Future of Artificial Intelligence

·         Summary of Artificial Intelligence concepts and techniques

·         Artificial Intelligence trends and future developments

·         Artificial Intelligence and society

·         Artificial Intelligence ethics and safety.

Yes