8 months (64 classes, 2 classes per week)
Month 1: Python Fundamentals for AI
Week 1: Basic Python
• Day 1-2: Python Data Types and Variables
o Introduction to basic data types: integers, floats, strings, and booleans.
o Variables and type conversion.
• Day 3-4: Control Structures (Loops & Conditional Expressions)
o if-else, for and while loops with examples.
o Practice with logical operators and condition handling.
Week 2: Python Libraries for AI
• Day 5-6: Introduction to Numpy and Pandas
o Basic operations in Numpy: array creation, indexing, slicing.
o Pandas for data handling: DataFrames, reading/writing CSVs.
• Day 7-8: Data Visualization with Matplotlib
o Plotting graphs, bar charts, histograms for data representation.
Month 2: Introduction to AI and Prompt Engineering
Week 3: General AI Introduction
• Day 9-10: Introduction to Artificial Intelligence
o Overview of AI, types of AI (narrow, general, super), practical examples.
• Day 11-12: Intro to Generative AI & Large Language Models (LLMs)
o Understanding LLMs, key terminology, and prompt-based generation.
Week 4: Using Open-Source AI Models
• Day 13-14: Introduction to OpenAI & Gemini Models
o Overview of using models from OpenAI and Gemini for generating responses.
• Day 15-16: Practical: Working with Pre-trained Models
o Simple program to interact with OpenAI GPT API.
Month 3: Machine Learning (ML)
Week 5: Huggingface & Transformers
• Day 17-18: Huggingface Library Overview
o Introduction to Transformers and Diffuser libraries, basic functions.
• Day 19-20: Transformers for Text-based Applications
o Text generation and sentiment analysis with pre-trained transformer models.
Week 6: Computer Vision and Audio
• Day 21-22: Computer Vision
o Introduction to computer vision, object detection using pre-trained models.
• Day 23-24: Audio Processing
o Understanding audio data, basic audio classification.
Month 4: Learning Techniques (Unsupervised & Supervised)
Week 7: Unsupervised Learning
• Day 25-26: Data Preparation with Pandas & Pytorch
o Hands-on dataset creation, using pandas and PyTorch for unsupervised learning.
• Day 27-28: Clustering Algorithms (K-means, DBSCAN)
o Practical implementation of unsupervised techniques.
Week 8: Supervised Learning
• Day 29-30: Dataset Creation & Model Training
o Using existing datasets or creating new datasets for model training.
• Day 31-32: Classification Models (Logistic Regression, Decision Trees)
o Training and evaluation of supervised learning models.
Month 5: Deep Learning
Week 9: Deep Learning Fundamentals
• Day 33-34: Introduction to Deep Learning
o Overview of deep learning concepts, neural networks, deep learning models.
• Day 35-36: Training Models on Large Datasets
o Practical: Implement deep learning using Pytorch, train models on complex
datasets.
Week 10: Making Models More Efficient
• Day 37-38: Hyperparameter Tuning
o Techniques for optimizing model performance.
• Day 39-40: Model Evaluation and Efficiency Improvement
o Evaluation metrics, model retraining to improve accuracy.
Month 6: Reinforcement Learning
Week 11: Basics of Reinforcement Learning
• Day 41-42: Introduction to RL Concepts
o Core principles: agent, environment, state, action, and rewards.
• Day 43-44: Simple Reinforcement Learning Algorithms
o Implement basic RL algorithms like Q-learning.
Week 12: Reinforcement Learning Application
• Day 45-46: Implementing Self-Learning Agents
o Program a simple RL agent to learn from its environment.
• Day 47-48: Training and Improving Prediction Models
o Fine-tuning RL models for better performance in decision-making.
Month 7: Math for AI and Robotics
Week 13: Calculus and AI
• Day 49: Introduction to Calculus in AI
o Understanding weights and biases, how calculus is used to optimize models.
• Day 50: Practical Example with Calculus
o Simple implementation of gradient descent using Pytorch.
Week 14: Linear Algebra for AI
• Day 51: Introduction to Linear Algebra in AI
o Feature engineering, data transformation, matrix operations for AI.
• Day 52: Practical: Applying Linear Algebra
o Hands-on example using linear algebra for data classification and validation.
Month 7: Neural Networks and Large Language Models (LLMs)
Week 15: Basic Neural Network Concepts
• Day 53: Introduction to Neural Networks
o Overview of the structure of neural networks, neurons, layers, activation
functions.
• Day 54: Creating Simple Neural Networks
o Practical: Create a simple neural network using Pytorch.
Week 16: Creating LLMs from Scratch
• Day 55: Learning the Basic Concepts of LLMs
o Introduction to the architecture of LLMs, pre-training and fine-tuning.
• Day 56: Basic Language Model Implementation
o Practical: Implement a basic LLM from scratch using available libraries.
Month 8: Robotics & Autonomous Systems
Week 17: Introduction to Robotics
• Day 57-58: Basics of Robotics and AI
o Overview of AI in robotics, types of robots, interaction between hardware and AI.
• Day 59-60: Interfacing Arduino with Python
o Practical: Control Arduino sensors using Python code.
Week 18: Autonomous Robotics
• Day 61-62: Introduction to Autonomous Systems
o Basics of computer vision, decision-making algorithms, and self-learning in
robotics.
• Day 63-64: Final Project: Implementing a Simple Autonomous Robot
o Build and program a basic robot with vision and decision-making capabilities
using sensors and Python.
