‭Digital Transformation Courses‬

‭Artificial Intelligence (AI)‬

‭Syllabus‬
❖
‭ ‬‭Learning Levels of the Syllabus‬
‭❖‬‭Theory‬
‭ .‬
1 I‭ ntroduction of Artificial Intelligence‬
‭2.‬ ‭History of Artificial Intelligence‬
‭3.‬ ‭Artificial Intelligence Ethics‬
‭4.‬ ‭Critical Concerned raised by AI‬
‭5.‬ ‭Russell Norvig - general learning agent‬
‭6.‬ ‭Machine Learning‬
‭6.1. Introducing Machine Learning‬
‭6.1.1. The Machine Learning Landscape‬
‭6.1.2. Different types of machine learning supervised learning‬
‭semi-supervised and reinforcement learning‬
‭6.1.3. Batch and online learning‬
‭6.1.4. Machine learning libraries Keras Tensor flow Pytorch‬
‭6.1.5. Machine learning tools Watson Dialogflow Luis Azure‬
‭cognitive service‬
‭6.1.6. The main challenge of ML‬
‭6.2. Anaconda Introduction‬
‭6.2.1. Anaconda Intro‬
‭6.2.2. Anaconda Installation ‬
‭6.2.3. Overview of Anaconda Packages‬
‭6.2.4. Installation of Jupyter Notebook‬
‭6.2.5. Conda Libraries‬
‭6.3. Python Introduction‬
‭6.3.1. Python Intro‬
‭6.3.2. Python Installation ‬
‭6.3.3. Overview of Python Packages‬
‭6.3.4. Numpy, Pandas, Lambda‬
‭6.3.5. Dealing with Missing Data‬
‭6.3.6. User Defined Functions, Classes and Objects‬
‭6.3.7. Visualization Intro ‬
‭6.3.8. Seaborn, Matloblib, etc‬
‭6.4. Statistics required for ML‬
 ‭6.4.1. Probability and Prob Density Function‬
‭6.4.2. Statistics - Methods‬
‭6.4.3. Types of Statistical Method‬
‭6.4.4. Conditional Probability‬
‭6.4.5. Standard Deviation and Coefficient Variation‬
‭6.4.6. Chebyshev Theorem‬
‭6.4.7. Empirical Rule‬
‭6.4.8. Five Number Summary and plots‬
‭6.4.9. Corelation Analysis‬
‭6.4.10. Rules for Computing Probability and Marginal‬
‭Probability‬
‭6.4.11. Bayes Theorem‬
‭6.4.12. Binomial, Poisson and Normal Distribution‬
‭6.4.13. Hypothesis Formulation - Null and Alternalte Hypothesis‬
‭6.4.14. Type I and Type II Errors‬
‭6.4.15. T-test, F-test and ANOVA‬
‭6.4.16. Chi Square‬
‭6.5. Supervised Learning‬
‭6.5.1. Lines Planes and Hyperplanes‬
‭6.5.2. Vector Algebra and Operations‬
‭6.5.3. Differential, Maxima and Minima of functions‬
‭6.6.4. Chain Rule, Maxima and Minima application in ML‬
‭6.6.5. Linear Regression - Part 1‬
‭6.6.6. Linear Regression - Part 2‬
‭6.6.7. Polynomial descent‬
‭6.6.8. Gradient curves‬
‭6.6.9. Multivariate Linear Regression‬
‭6.6.10. Categorical Independent Variables‬
‭6.6.11. Root mean square Error and Mean Absolute Error‬
‭6.6.12. Logistic Regression‬
‭6.6.13. Threshold Setup, Precision and Recall‬
‭6.6.14. Naïve Bayes‬
‭6.6.15. KNN‬
‭6.6.16. SVM‬
‭6.6. Ensemble Techniques‬
‭6.6.1. Decision Trees Intro‬
‭6.6.2. Decision Trees – CART‬
‭6.6.3. Ensemble Techniques‬
 6‭ .6.4. Random Forests‬
‭6.6.5. Bagging‬
‭6.6.6. Boosting‬
‭6.6.7. Stacking‬
‭6.7. Unsupervised Learning‬
‭6.7.1. Clustering Intro‬
‭6.7.2. Types of Clustering‬
‭6.7.3. Types of Clustering Algorithm‬
‭6.7.4. K Means Clustering‬
‭6.7.5. Importance of Scaling‬
‭6.7.6. K-means Clustering Pros and Cons‬
‭6.7.7. K means Silhouette coefficient‬
‭6.7.8. Dynamic Clustering‬
‭6.7.9. Hierarchical Clustering‬
‭6.7.10. Cophenetic Correlation‬
‭6.7.11. Principal Component Analysis‬
‭6.8. Feature Engineering‬
‭6.8.1. Regularization Models‬
‭6.8.2. Lasso and Ridge Regression‬
‭6.8.3. Feature Engineering Intro‬
‭6.8.4. Cross Validation (K-fold)‬
‭6.8.5. Bootstrap Sampling‬
‭6.8.6. Leave one out Cross Validation‬
‭6.8.7. Up Sampling and Down Sampling‬
‭6.8.8. Model Tuning and Performance‬
‭6.8.9. ROC and AUC‬
‭6.8.10. Hyper Parameters and Tuning‬
‭6.8.11. GridSearch‬
‭6.9. Machine Learning Tools‬
‭6.9.1. IBM Watson‬
‭6.9.2. Google Dialogflow‬
‭6.9.3. Microsoft Luis‬
‭7.‬ ‭Image Processing‬
‭7.1. Introducing Image Processing‬
‭7.2. Packages of Image Processing‬
‭7.3. Basic Operation on Image‬
‭7.4. Geometric Opeartion on Image‬
‭7.5. Radiometric Operation on Image‬
 ‭ .6. Object Detection using Image Processing‬
7
‭7.7. Live Image Capturing & Processing‬
‭7.8. Live Video Processing‬
‭7.9. Image Processing Tools‬

‭8.‬ D ‭ eep Learning‬

‭8.1. Introduction on Deep Learning‬
‭8.2. Deep Learning Working Process‬
‭8.3. Packages Installation‬
‭8.4. Classification & Prediction‬
‭8.5. Underfitting & Overfitting‬
‭8.6. Encoding & Embedding‬
‭8.7. CNN‬
‭8.8. RNN‬
‭8.9. LSTM‬
‭8.10. VAE‬
‭8.11. Basic of GAN‬
‭9.‬ ‭Neural Network‬
‭9.1. Introduction on Neural Network‬
‭9.2. Neural Network Working Process‬
‭9.3. Packages Installation‬
‭9.4. Layers of Neural Network‬
‭9.5. Activation Function‬
‭9.6. ReLU‬
‭9.7. Loss Function‬
‭9.8. Forward Propagation‬
‭9.9. Backward Propagation‬
‭10.‬‭Sentiment Analysis‬
‭10.1. Introduction to Sentiment Analysis‬
‭10.2. Package Installation‬
‭10.3. Sentiment Analysis of Movie Review‬
‭10.4. Twitter Sentiment Analysis‬
‭10.5. Emotion Detection using Sentiment Analysis‬
‭11.‬‭Natural Language Processing‬
‭11.1. Introduction on Natural Language Processing‬
‭11.2. Packages Installation‬
‭11.3. Text classification‬
‭11.4. Building a "fake news" classifier‬
 ‭12.‬‭Speech Recognition‬
‭12.1. Introducing Speech Recognition‬
‭12.2. Packages Installation‬
‭12.3. Speech to Text Conversion‬
‭12.4. Feature Extraction from Speech‬
‭12.5. Speech Recognizer‬
‭12.6. MY ASSISTENT Build up‬
‭13.‬‭Case Studies‬
‭13.1. Rolls-Royce And Google Partner To Create Smarter,‬
‭Autonomous Ships Based On AI And Machine Learning‬
‭13.2. Microsft’s 2030 vision on Healthcare, Artificial Intelligence, Data‬
‭and Ethics‬
‭13.3. The Incredible Ways John Deere Is Using Artificial‬
‭Intelligence To Transform Farming‬
‭13.4. How McDonald's Is Getting Ready For The 4th Industrial‬
‭Revolution Using AI, Big Data And Robotics‬
‭13.5. Google-Funded Company Uses Artificial Intelligence To Fight‬
‭Against Fake News‬
‭13.6. Jaguar Land Rover Is Getting Ready For The 4th Industrial‬
‭Revolution: AI & Autonomous Cars‬
‭13.7. The Amazing Ways Chinese Tech Giant Alibaba Uses Artificial‬
‭Intelligence And Machine Learning‬
‭13.8. The Amazing Ways How Wikipedia Uses Artificial Intelligence‬
‭13.9. IBM Showcases Artificial Intelligence Superiority With Project‬
‭Debater‬
‭13.10. How The UK Government Uses Artificial Intelligence To Identify‬
‭Welfare And State Benefits Fraud‬

‭❖‬‭Practical‬
‭⮚‬ ‭Machine Learning‬
‭1.‬ ‭Dealing with Missing Data‬
‭2.‬ ‭User Defined Functions, Classes and Objects‬
‭3.‬ ‭Visualization‬
‭4.‬ ‭Seaborn, Matplotlib, Pandas‬
‭5.‬ ‭Probability Density Function‬
‭6.‬ ‭Conditional Probability‬
‭7.‬ ‭Standard Deviation and Coefficient Variation‬
‭8.‬ ‭Chebyshev Theorem‬
9‭ .‬ ‭Empirical Rule‬
‭10.‬ ‭Five Number Summary and plots‬
‭11.‬ ‭Correlation Analysis‬
‭12.‬ ‭Rules for Computing Probability and Marginal Probability‬
‭13.‬ ‭Marginal Probability‬
‭14.‬ ‭Bayes Theorem‬
‭15.‬ ‭Binomial Distribution, Poisson Distribution, Normal‬
‭Distribution‬
‭16.‬ ‭Hypothesis Formulation - Null and Alternate Hypothesis‬
‭17.‬ ‭T-test, F-test and ANOVA‬
‭18.‬ ‭Lines Planes and Hyperplanes‬
‭19.‬ ‭Maxima and Minima of functions‬
‭20.‬ ‭Chain Rule, Maxima and Minima application in ML‬
‭21.‬ ‭Linear Regression‬
‭22.‬ ‭Polynomial descent‬
‭23.‬ ‭Gradient curves‬
‭24.‬ ‭Multivariate Linear Regression‬
‭25.‬ ‭Root mean square Error and Mean Absolute Error‬
‭26.‬ ‭Logistic Regression‬
‭27.‬ ‭Threshold Setup, Precision and Recall‬
‭28.‬ ‭Naive Bayes‬
‭29.‬ ‭KNN‬
‭30.‬ ‭SVM‬
‭31.‬ ‭Decision Trees Intro‬
‭32.‬ ‭Decision Trees - CART‬
‭33.‬ ‭Random Forests‬
‭34.‬ ‭Bagging‬
‭35.‬ ‭Boosting‬
‭36.‬ ‭Stacking‬
‭37.‬ ‭Types of Clustering Algorithm‬
‭38.‬ ‭K Means Clustering‬
‭39.‬ ‭K means Silhouette coefficient‬
‭40.‬ ‭Hierarchical Clustering‬
‭41.‬ ‭Cophenetic Correlation‬
‭42.‬ ‭Principal Component Analysis‬
‭43.‬ ‭Lasso and Ridge Regression‬
‭44.‬ ‭Feature Engineering Intro‬
‭45.‬ ‭Cross Validation (K-fold)‬
 4‭ 6.‬ ‭Bootstrap Sampling‬
‭47.‬ ‭Leave one out Cross Validation‬
‭48.‬ ‭Up Sampling and Down Sampling‬
‭49.‬ ‭ROC and AUC‬
‭50.‬ ‭GridSearch‬
‭51.‬ ‭Visual Recognition using IBM Watson‬
‭52.‬ ‭Chatbot using Google Dialogflow‬
‭53.‬ ‭Chatbot using Microsoft LUIS‬
‭54.‬ ‭Appendix‬

‭⮚‬ ‭Image Processing‬

‭1.‬ ‭Basic Operation on Image‬
‭2.‬ ‭Geometric Opeartion on Image‬
‭3.‬ ‭Radiometric Operation on Image‬
‭4.‬ ‭Object Detection using Image Processing‬
‭5.‬ ‭Live Image Capturing & Processing‬
‭1.‬ ‭Live image capturing through Webcam‬
‭2.‬ ‭Video Feeding‬
‭3.‬ ‭Blurring‬
‭4.‬ ‭Color filtering‬
‭5.‬ ‭Edge Detection‬
‭6.‬ ‭Face & Eye Detection‬
‭6.‬ ‭Live Video Processing‬
‭⮚‬ ‭Deep Learning‬
‭1.‬ ‭Classification & Prediction‬
‭2.‬ ‭Underfitting & Overfitting‬
‭3.‬ ‭Encoding & Embedding‬
‭4.‬ ‭CNN‬
‭5.‬ ‭RNN‬
‭6.‬ ‭LSTM‬
‭7.‬ ‭VAE‬
‭8.‬ ‭GAN‬
‭9.‬ ‭Special of Deep Learning‬
‭⮚‬ ‭Neural Network‬
‭1.‬ ‭Complete Neural Network Building‬
‭⮚‬ ‭Sentiment Analysis‬
‭1.‬ ‭Simplifying Sentiment Analysis‬
‭2.‬ ‭Sentiment Analysis Walkthrough‬
 3‭ .‬ ‭Sentiment Analysis of Movie Review‬
‭4.‬ ‭Twitter Sentiment Analysis Type 1‬
‭5.‬ ‭Twitter Sentiment Analysis Type 2‬
‭6.‬ ‭Real Time Emotion Detection‬
⮚
‭ ‬ ‭Natural Language Processing‬
‭1.‬ ‭Text classification‬
‭2.‬ ‭Building a "fake news" classifier‬
‭⮚‬ ‭Speech Recognition‬
‭1.‬ ‭Speech to Text Conversion‬
‭2.‬ ‭Feature Extraction from Speech‬
‭3.‬ ‭Speech Recognizer‬
‭4.‬ ‭My Assistant (Similar to Alexa, Google My Assistant)‬