Artificial Intelligence Course Syllabus

Module 1: Introduction to Data Science

• What is Data Science?
• Introduction to Machine Learning, Deep Learning, and AI
• Overview of Data Analytics and its types (Descriptive, Predictive, Prescriptive)

Module 2: Introduction to Python

• What is Python and why is it used?
• How to install Python
• Introduction to Python IDEs (Integrated Development Environments)
• Overview of Jupyter Notebook

Module 3: Python Basics

• Understanding basic data types
• Working with lists and slicing data
• Using IF statements and loops
• Creating and managing dictionaries and tuples
• Writing functions
• Working with arrays
• Selecting data by position and labels

Module 4: Python Packages

• Introduction to key libraries:
• Pandas for data manipulation
• NumPy for numerical computations
• Scikit-Learn for machine learning
• Matplotlib for data visualization

Module 5: Importing Data

• How to read data from CSV files
• Saving data in Python
• Loading and managing Python data objects
• Writing data back to CSV files

Module 6: Manipulating Data

• Selecting rows and columns
• Rounding numbers
• Merging datasets
• Aggregating data
• Common data cleaning and transformation techniques

Module 7: Statistics Basics

• Measures of central tendency: Mean, Median, Mode
• Understanding skewness and normal distribution
• Basics of probability:
• Definitions and types
• Odds ratio
• Variance and standard deviation
• Bias-variance trade-off
• Underfitting vs. overfitting
• Distance metrics:
• Euclidean Distance
• Manhattan Distance
• Outlier detection and analysis:
• Interquartile range (IQR)
• Box plots and scatter plots
• Cook’s distance
• Handling missing values:
• What is NA (Not Available)?
• Central imputation and KNN imputation
• Correlation analysis:
• Pearson correlation
• Positive and negative correlations

Module 8: Error Metrics

• Classification Metrics:
  
• Confusion matrix
• Precision, Recall, and F1 Score
• Specificity
• Regression Metrics:

• Mean Squared Error (MSE)
• Root Mean Squared Error (RMSE)
• Mean Absolute Percentage Error (MAPE)

Module 9: Machine Learning

1. Supervised Learning
• Linear Regression:
• Understanding linear equations, slope, intercept, R-squared
• Logistic Regression:
• Odds ratio, probability of success/failure, ROC curve
• Bias-Variance trade-off

1. Unsupervised Learning
• K-Means Clustering
• K-Means++
• Hierarchical Clustering
2. Support Vector Machines (SVM)
   
• Concepts of support vectors and hyperplanes
• Linear hyperplanes and SVM kernels
3. SVM Kernels
   
• Linear, Radial, and Polynomial kernels
4. Other Machine Learning Algorithms
• K-Nearest Neighbors (KNN)
• Naïve Bayes Classifier
• Decision Trees (CART and C5.0)
• Random Forests

Module 10: Artificial Intelligence

• Introduction to AI concepts
• Understanding perceptrons and multi-layer perceptrons
• Markov Decision Processes
• Logical agents and first-order logic
• Applications of AI in real-world scenarios

 Module 11: Deep Learning Algorithms

• Convolutional Neural Networks (CNN)
• Recurrent Neural Networks (RNN)
• Artificial Neural Networks (ANN)

Introduction to Natural Language Processing (NLP)

• Text pre-processing techniques:
• Noise removal
• Lexicon normalization (Lemmatization and Stemming)
• Object standardization

Text to Features (Feature Engineering)

• Syntactical parsing
• Dependency grammar
• Part of Speech (POS) tagging
• Entity parsing and named entity recognition (NER)
• Topic modeling
• N-grams and TF-IDF
• Word embeddings and feature extraction

Tasks of NLP

• Text classification
• Text matching:
• Levenshtein distance
• Phonetic and flexible string matching