1.1: Installing Python, setting up Jupyter/VS Code and managing packages (pip/conda)

1.2: Basic syntax: variables, expressions and data types

1.2: Control flow: conditionals and loops (if, for, while)

1.4: Functions, simple modules and code organization

1.5: Core containers: lists, tuples, dictionaries and sets

1.6: Intro to NumPy arrays for Numerical Work

2.1: Loading And Inspecting Tabular Data with Pandas

2.2: Cleaning Data: Missing Values, Type Conversions and Basic Fixes

2.3: Aggregation And Grouping (Summaries, Pivots)

2.4: Simple Visualizations with Matplotlib / Seaborn

2.5: Basic Descriptive Statistics (Mean, Median, Variance)

2.6: Communicating Insights from Exploratory Analysis

3.1: ML Workflow: Data → Model → Evaluation

3.2: Supervised Learning Overview: Regression Vs Classification

3.3: Simple Models: Linear Regression and Logistic Regression (Intuition + scikit-learn)

3.4: k-Nearest Neighbors and Decision Tree Intuition

3.5: Train/Test Split, Cross-Validation Basics and Overfitting/Underfitting

3.6: Key Metrics: Accuracy, Precision, Recall, F1, Confusion Matrix

4.1: Feature Engineering Basics: Creating Useful Inputs from Raw Data

4.2: Managing Categorical Variables (Label, One-Hot Encoding)

4.3: Scaling And Normalization (Why and When to Use)

4.4: Feature Selection Techniques (Filter / Wrapper Ideas)

4.5: Model Evaluation Strategies and Validation Pipelines (K-Fold, Holdout)

4.6: Simple Hyperparameter Search Using GridSearchCV / RandomizedSearchCV

5.1: What A Neuron and Layer Do: Intuition for MLPs (Feedforward Nets)

5.2: Common Activation Functions and Why They Matter (ReLU, Sigmoid)

5.3: Loss Functions and The Idea of Gradient-Based Learning (No Heavy Calculus)

5.4: Overfitting Controls: Dropout, Early Stopping, Simple Regularization Ideas

5.5: Building A Small Neural Network with TensorFlow/Keras or PyTorch (Hands-On)

6.1: Why Sequences Need Special Models (Order and Context)

6.2: Recurrent Neural Networks: Core Idea and Limitations

6.3: LSTM And GRU: Gating Intuition and When to Use Them

6.4: Preparing Sequence Data: Tokenization, Padding, Batching

6.5: Simple Sequence Tasks: Sentiment Classification or Next-Token Prediction

7.1: Motivation For Attention: Focusing On Relevant Parts of Input

7.2: High-Level Transformer Architecture (Encoder/Decoder Idea)

7.3: Self-Attention and Multi-Head Attention Explained Simply

7.4: Positional Encoding: How Order Is Represented Without Recurrence

7.5: Using Pre-Trained Transformer Models with Hugging Face (Practical Demos)

8.1: Text Cleaning and Normalization: Tokenization, Stop-Words, Lemmatization

8.2: Text-To-Numbers: Bag-Of-Words, TF-IDF And Quick Intro to Embeddings

8.3: Word Embeddings (word2vec / GloVe) And Contextual Embeddings Overview

8.4: Retrieval-Based Vs Generative Chatbot Approaches (Pros/Cons)

8.5: Dialog Data Formats and Preparing a Small Conversational Dataset

8.6: Quick Hands-On: Run A Pre-Trained Transformer to Generate or Rank Replies

9.1: Choose Approach: Fine-Tune Small Transformer or Wire Up a Pre-Trained Conversational Model

9.2: Implement Conversational Flow: Prompt Design, Context Handling, Turn-Taking

9.3: Simple Interface Options: Console Demo, Basic Web Form or Messaging Mockup

9.4: Evaluating Responses: Human Review, Automated Heuristics and Basic Metrics

9.5: Practical Deployment Notes: APIs, Lightweight Hosting, Rate-Limits

9.6: Ethical & Safety Checklist: Bias, Privacy, Misuse Prevention

9.7: Final Deliverable: Working Chatbot Demo + Short Report Explaining Design and Limitations