CURRICULUM
Complete Course Syllabus
7 comprehensive modules covering everything from Python programming to cutting-edge Generative AI.
MODULE 01
Python Programming
Foundation
Introduction to AI & Definition and Scope
Introduction to Programming
Google Colab Setup
Why Python?
Data Types & Type Conversion
Variables
Operators — Arithmetic, Comparison, Logical, Assignment, Membership, Identity, Bitwise
If-else & Nested If-else
For Loops & While Loops
Break, Continue and Pass
Strings — Multiline, Patterns, Zero Padding
F-strings & Performance vs format()
String Functions: strip(), split(), join(), capitalize(), lower(), title(), upper(), istitle(), replace()
Lists — Creation, Retrieval, Item Replacement
List Comprehension & Mutable Concept
Nested Lists
List Functions: len(), append(), pop(), insert(), remove(), sort(), reverse()
Forward & Backward Indexing
Forward, Backward & Step Slicing
Sets — Creation, union(), intersection(), difference(), add(), remove(), pop()
Tuples — Creation, Immutable Concept, Concatenate, Unpacking
Tuple Functions: len(), count(), index(), sorted(), zip()
Dictionaries — Creation, Keys:Values Concept
Creating CSV from Python Dictionary
Dictionary Functions: keys(), values(), items(), get(), pop(), update(), from_dict(), zip(), clear(), map()
Functions — Inbuilt vs User Defined
Types of Function Arguments
Global vs Local Variables
Anonymous Function (LAMBDA)
File Handling — read, write, append modes
MODULE 02
Python Libraries — Pandas & NumPy
Data Manipulation
Pandas Introduction
Series — Creating, Empty Series, Series from List/Array/Column
Index in Series & Accessing Values
Statistical Operations on Series
NaN Values & Keywords: Values, index, dtypes, size
Python List vs Numpy Array vs Pandas Series
Series Functions: head(), tail(), sum(), count(), nunique(), sort_values(), value_counts()
DataFrames Introduction
Creating DataFrames from Lists, Dictionaries, Arrays
Creating DataFrames from CSV, Excel, and Other File Formats
DataFrame Attributes: shape, size, dtypes, index, columns
DataFrame Methods: head(), tail(), info(), describe()
Accessing and Modifying Data: loc, iloc
Adding and Dropping Columns and Rows
Renaming Columns and Index
Identifying Missing Data
Handling Missing Data: fillna(), dropna()
Replacing Values
Filtering Data
Sorting DataFrames
Applying Functions: apply(), map()
Grouping Data: groupby()
Merging and Joining DataFrames
Concatenating DataFrames
Setting and Resetting Index
MultiIndex (Hierarchical Indexing)
Mathematical and Statistical Operations
Aggregation Methods: sum(), mean(), count(), nunique()
Pivot Tables and Cross-tabulations
Transpose of a DataFrame
Inplace Parameter & Ampersand (&) Logical Operator
NumPy — Importance in Data Science
Creating NumPy Arrays from Lists and Tuples
arange(), linspace(), logspace()
zeros(), ones(), full()
Random Numbers: random(), rand(), randn(), randint()
Array Attributes: shape, size, ndim, dtype, itemsize
Array Manipulation, Mathematical Operations, Indexing & Slicing
NumPy Functions: add(), subtract(), multiply(), divide(), arange(), log(), abs(), reshape(), ravel(), flatten()
Statistics: mean(), median(), std(), sum(), min(), corrcoef(), cov()
List vs Array Performance Comparison
Diagonal, Trace & Identity Matrix
Multiplicative Inverse, Determinant & Adjoint Matrix
Parsing, Adding and Subtracting Matrices
MODULE 03
Statistics for Data Science
Mathematical Foundation
What are Statistics?
Measures of Central Tendency — Mean, Median, Mode
Measures of Dispersion — Range, Variance, Standard Deviation
Numerical Data — Continuous and Discrete
Categorical Data — Nominal and Ordinal
Descriptive Statistics
Inferential Statistics
Prescriptive Statistics
Population and Types of Sampling Techniques
Random Sampling
Systematic Sampling
Stratified Random Sampling
Cluster Sampling
Percentiles and Quantiles — 25%, Median, 75%
Skewness — Right Skew, Left Skew
Normal Distribution
Difference between Independent and Dependent Variables
Correlation — Positive, Negative, Zero
Multicollinearity & Variance Inflation Factor
Causation
Central Limit Theorem
Normalization Types — Standard Scaler, Min-Max Scaler
Outliers — Z-Score, Box-Plot, IQR
Hypothesis Testing
Chi-Squared Test
Conditional Probability
MODULE 04
Machine Learning
Core ML Algorithms
What is Machine Learning?
Traditional Programming vs Machine Learning
Types of ML — Supervised, Semi-Supervised, Unsupervised, Reinforcement Learning
Classification — Binary, Multi-Class, Multi-Label
Regression
Instance Based vs Model Based Learning
ML Pipeline — ETL, EDA, Training, Validation, Testing, Deployment, Monitoring
Gradient Descent
Simple Linear Regression
Linear Regression Assumptions & Best Fit Line
Cost Function & Loss Optimization (Least Squares)
Gradient Descent Algorithm
Evaluation Metrics — MAE, MSE, RMSE, MSLE, R², Adjusted R²
Residual (Error) Analysis
Homoscedasticity & Heteroscedasticity
Multicollinearity & VIF Math
Recursive Feature Elimination (RFE)
Multiple Linear Regression
Logistic Regression — Types, Why Not Linear for Classification?
Logistic Model — Sigmoid Curve & Activation Function
Interpretation of Coefficients & Decision Boundary
Cost Function of Logistic Regression
Gradient Descent in Logistic Regression
Confusion Matrix — Accuracy, Precision, Recall, F1-Score
ROC Curve and AUC
Classification Report in Python
Decision Tree — Introduction, Types (Classification & Regression)
Decision Tree Training Algorithm — Entropy, Information Gain, Gini Index
Feature Selection & Node Splitting Technique
Decision Tree Feature Importance & Model Evaluation
Limitations of Decision Tree
Ensemble Learning — Bagging (Bootstrap Aggregation)
Random Forest — Classification & Regression
Advantages of Random Forest over Decision Trees
Random Forest Feature Importance & Model Evaluation
Gradient Boosting Machine (GBM) — Boosting
Bagging vs Boosting
GBM Classification & Regression
XGBoost — Introduction & Types (Classification & Regression)
XGBoost Feature Importance & Advantages
Model Evaluation — ROC Curve & AUC, Benchmarking
K Fold Cross Validation
Stratified K Fold Cross Validation
LOOCV & Hold Out CV
Hyperparameter Tuning — GridSearchCV, RandomizedSearchCV
HyperOpt — Bayesian Optimization
Model Calibration
Model Interpretability & Explainability
Overfitting and Underfitting
KNN Algorithm & KNN Imputation
Euclidean Distance & Manhattan Distance
L1 (Lasso), L2 (Ridge) & Elastic Net Regularization
Encoding Techniques — One-Hot, Label, Ordinal Encoder
SMOTE
Naïve Bayes
K-Means Clustering
Harmonic Mean
MODULE 05
Natural Language Processing (NLP)
Text AI
Introduction to NLP
Tokenization Techniques
Tokenization in spaCy
Text Cleaning — regex, lowercasing, punctuation removal
Part-of-Speech (POS) Tagging
Stemming & Lemmatization
Stop Words
Introduction to Text Representations
Label and One-Hot Encoding
Bag of Words
TF-IDF
N-Grams Based Text Representations
Word Embeddings
Word2Vec — Continuous Bag of Words (CBOW), Skip Gram
Advanced Embeddings — GloVe, ELMo & Transformer Based Embeddings
Use Case — Sentiment Classification with Embedding & ANNs
Cosine Similarity
N-grams
MODULE 06
Deep Learning
Neural Networks
Introduction to Neural Networks
Activation Functions — Sigmoid, Tanh, ReLU and Variants, Softmax
ANN and Perceptron
RNN — Concept and Need for Sequential/Time-Series Data
Comparison with Fully Connected Networks
RNN Architecture — Input, Hidden, and Output Layers
Hidden State and Recurrence Relation
Unfolding Through Time
Types of RNN
Challenges in RNN
Federated Learning
LSTM — Concept and Motivation: Overcoming Vanishing Gradient
Memory Cells and Gates Introduction
LSTM Architecture — Cell State and Long-Term Memory
Forget Gate, Input Gate, Output Gate
Updating Hidden and Cell States
Working of LSTM — Step-by-Step Mathematical Formulation
Intuition Behind Gate Operations
LSTM Implementation in Python (Keras/TensorFlow)
Comparison: RNN vs LSTM vs GRU
Use Case — Sentiment Analysis/Text Classification with LSTM
Transfer Learning
Autoencoders — Encoder-Decoder Concept
Encoder-Decoder Implementation with TensorFlow
Variational Autoencoders (VAE)
GAN (Generative Adversarial Networks) — Basic Introduction
MODULE 07
Generative AI
Frontier AI
Transformer Architecture — Understanding in Depth
Self Attention & Multi-Headed Attention
Positional Encoding
Transformer Implementation with TensorFlow
Machine Translation — English to German Translation Model
Large Language Models (LLMs)
Gemma, LLaMA, Mistral & Other Open-Source LLMs via Hugging Face
Practical Applications with Open-Source LLMs for Real-World Use Cases
Introduction to Retrieval-Augmented Generation (RAG)
Introduction to LangChain
LangGraph
LlamaIndex
LangSmith
Prompt Engineering — Principles of Prompt Design
Few-Shot, Zero-Shot, Chain-of-Thought Prompting
Advanced Prompting Techniques for Optimal AI Responses
AI Agents — Building Intelligent Systems & Exploring Future AI Developments
