Introducing AI With Python

Live: Online

Rs 12,500/- PKR

About Course

This course provides an engaging introduction to programming, data science, and AI through Python and PyTorch. Students will explore fundamental programming concepts, visualize data, work on real-world mini projects, and delve into object detection and chatbot development using industry-standard tools. The hands-on nature of the course encourages creativity, experimentation, and collaboration, preparing students for deeper learning in AI and machine learning.

Class 1: Python Basics & Introduction to PyTorch

Variables, data types, and simple operations
Conditional statements (if, else)
Loops (for, while)
Functions (definition, parameters, return)
Lists and basic data structures
Introduction to PyTorch tensors:
- What are tensors?
- Creating and manipulating tensors
- Playground setup: Google Colab or Jupyter Notebooks

Class 2: Practicing with Loops, Functions + Mini Project Prep

Recap and deeper practice with loops and functions
Using PyTorch to generate random tensors and apply basic operations
Mini Project: Simulate a Dice Rolling Game
- Generate random numbers using PyTorch
- Track stats (e.g., average rolls, frequency)
- Create a modular structure using functions
- Collaborative playground creation + code snippets
- Encourage creative extensions (e.g., multi-dice simulation)

Class 3: Data Visualization Basics

Introduction to Matplotlib and Seaborn
Types of graphs: Line plot, Bar chart, Histogram, Pie chart
Plotting datasets (e.g., temperature, test scores)
Aesthetic customization (titles, labels, legends, colors)

Class 4: Real-World Visualizations + Final Project Discussion

Applications:
- COVID-19 daily cases
- Visualizing students' marks or performance trends
- Simulated data for expenses and budgeting
- Brief intro to interactivity using Plotly
Project: Create a Dashboard of Your Day
- Collect 1-day time usage data (sleep, study, screen time, etc.)
- Visualize it with pie charts, bar graphs
- Display insights like “most productive hour”
- Optional: Compare multiple days, integrate basic PyTorch stats

Class 5: Concept of Object Detection + MMDetection Setup

What is object detection? How is it different from classification?
Introduction to MMDetection framework
Using pretrained models (YOLO, Faster R-CNN)
Installation and setup (Colab/Runtime notes)
Loading an image and detecting objects
Visualizing detection results with bounding boxes

Class 6: Real-World Applications of Object Detection

Applications:
- Object detection in security cameras
- Detecting traffic signs or vehicles
- Custom example: Book detection on a shelf
- Minor tweaking with confidence thresholds and image sources
Project: Object Detector for Everyday Items
- Upload your own room image
- Detect known objects
- Present findings and reflection
- Discuss challenges and limitations (e.g., model size, accuracy)

Class 7: Chatbots & Conversational AI

Introduction to Chatbots
Rule-based vs. AI-powered
Using a simple transformer-based model (e.g., DialoGPT or GPT-2)
Build a chatbot that can respond to basic queries
Exploring model inference using Hugging Face Transformers
Limitations and ethical considerations

Class 8: Project + RAG Discussion

Project: Build Your Own Chatbot
- Create a chatbot that can answer FAQ-style questions (e.g., about a topic like space, animals, school subjects)
- Train/infer using predefined context
Intro to RAG (Conceptual)
- Why large models struggle with specific info
- How RAG uses external data sources to improve responses
- Real-world examples (chatbots with document support)

What Will You Learn?

Writing Python programs using variables, conditionals, loops, and functions.
Creating and manipulating tensors with PyTorch for simulations and experiments.
Building simulations like dice games using randomness and modular code.
Visualizing data with Matplotlib and Seaborn, including pie charts and bar graphs.
Understanding object detection and applying pretrained models on real-world images.

Exploring use cases of AI in everyday life—like detecting books or traffic signs.
Building and customizing your own chatbot with transformer models like GPT-2.
Gaining insights into Retrieval-Augmented Generation (RAG) and how AI can access external knowledge to improve responses.
Developing a solid foundation in programming, data visualization, AI applications, and ethical tech usage.

Recorded Lectures

With lifetime access to our lecture content,
you can revisit and refresh your concepts at your convenience.

Lecture 01: Python Fundamentalss

Integer
Float
String
Boolean
Character
String operations
Type conversion
Lists
Tuples
Sets
Problem solving prime/composite, perform set operations

Homework 1

Lecture 02: Problem Solving(Tutorial)

Removeing duplicates from list and sorts it
Finding union of two lists (unique + sorted)
Finding elements in H not in D (H − D)
Generating all ordered pairs (Cartesian product)
Checking if a number is prime
Checking if a number is composite
Returning absolute value of a number
Separateing negatives and positives
Converting a number into its binary representation

Lecture 03: Lists And Comprehension

Filter fruits containing “a”, sort, reverse
List comprehension with length filter
Prime check with list comprehension (non-primes)
Measure execution time with loops vs comprehension
Sorting lists (original vs sorted copy)
Sort words alphabetically, reverse, or by length
Sort words with custom keys (like first 2 letters)
Functions: define, call, pass params, default values
Functions with return values (single & multiple)
Type hints, assertions for type safety
Segregate uppercase and lowercase letters
Process numbers, skip negatives (pass)
Yield vs return (generators vs normal functions)
Row-wise maximum in 2D array

Homework 2

Lecture 04:NumPy

Mixed types in lists, single type in NumPy arrays.
Array creation using np.array(), np.zeros(), np.ones(), np.arange().
Shape with .shape, reshape arrays using .reshape().
Indexing and slicing with [ ] and : operators.
Math operations + - * / ** work elementwise on arrays.
Broadcasting auto-expands smaller arrays to match larger ones.
Discount calculation using vectorized array operations.
Random numbers with np.random.randint(low, high, size).
Statistics with np.sum(), np.mean(), np.max(), np.min().
Boolean masking with conditions and np.where() for filtering/replacing.

Homework 3

Lecture 05:Assignment 03(Tutorial)

Task 1: Created a sequence with np.arange, transformed values, reshaped into a 10×10 matrix, and flattened back into 1D.
Task 2: Generated random sensor readings (5×4), subtracted sensor offsets (1D broadcasting), applied scalar subtraction for maintenance cost, and obtained final calibrated readings.
Task 3: Performed statistical analysis with max, mean, row-wise averages, column-wise sums, and accessed a specific reading using indexing.
Task 4: Applied discounts on item prices, converted percentages to decimals, calculated final prices as floats, then cast them into integers using np.int64.
Task 5: Simulated 500 die rolls, counted sixes, reshaped results into blocks, and computed block-wise averages with np.mean.

Lecture 06:Boolean Masking

Boolean masking uses conditions (arr % 2 == 0, arr % 5 == 0) and np.where() to replace values.
Row-wise and column-wise counts with .sum(axis=0/1).
Sorting arrays with np.sort(), reverse using [::-1].
Slicing arrays with [::-1] (reverse), [:3] (first 3), ::2 (even index), 1::2 (odd index).
Views share data with the original array, copies (.copy()) are independent.
Iteration through arrays with nested loops to extract values.
Boolean indexing like arr[arr > 3] filters directly, np.where() gives indexes.
Concatenation with np.concatenate, np.hstack, np.vstack, np.dstack for combining arrays.
Practical example: combining student scores using stacking.
enumerate() modifies arrays/lists in place while looping.
Splitting arrays with np.array_split(arr, n, axis) for horizontal or vertical slicing.

Homework 4

Lecture 07:Dictionaries

Created dictionary with items and prices.
Accessed dictionary values using keys.Checked if key exists in dictionary.
Updated values and added new keys.
Created tuple and unpacked variables.
Looped dictionary and updated values.
Counted keys using len().
Built new dict with comprehension.
Defined function with **kwargs.
Mixed parameters with *args and **kwargs.
Created lambda for cube, add, subtract.
Checked odd and prime with lambda.
Squared numbers using map().
Combined map and filter together.Sorted list by closeness to 10.
Applied lambda on NumPy array.
Created closure multiplier function.
Built doubler and tripler functions.

Homework 5

Lecture 08:Candy Shop Project

Simulated a candy shop with lists, sorting, filtering, counting, and a guessing game.
Created candies and prices lists.
Filtered candies containing letter “a”.
Sorted candies by closeness to price 4.
Separated even and odd prices.
Created candy multiplier using lambda.
Made 2D candy basket and zigzag traverse.
Made “Guess the Candy Price” game.

Lecture 09:Object Oriented Programming

Created Student class with name, age, and grade.
Printed student info using __str__().
Made MyClass with class and instance attributes.
Changed and printed class attribute from instance.
Created Person class that prints all attributes dynamically.
Added extra attributes like dob, grade, address.
Built ShoppingCart with add_item() and show_cart().
Added fruits and displayed full cart.
Defined Point class storing coordinates as tuple.
Displayed point location using display().
Created Car class with color, model, and state flag.
Added subject marks using add_mark().
Calculated total and percentage in show_percentage().
Imported Path, NumPy, and PIL for image handling.
Built DataLoader to load images from folder.
Used matplotlib to show all loaded images.
Loaded and displayed all cat and dog pictures.
Extracted and showed Red, Green, and Blue channels separately using NumPy slicing.

Homework 6