ML / AI
Important note : Do not submit assignments against sample lectures if you have not purchased ML / AI course
Essential Math
ML / AI
NumPy Vector Operations
ML / AI
NumPy Matrix Operations (Part 1)
ML / AI
NumPy Matrix Operations (Part 2)
ML / AI
NumPy Matrix Operations (Part 3)
ML / AI
Bug Correction (Previous Session)
ML / AI
NumPy Matrix Operations (Part 4)
ML / AI
matplotlib (Part 1)
ML / AI
matplotlib (Part 2)
ML / AI
Statistics (Part 1)
ML / AI
Statistics (Part 2)
ML / AI
Assignment - 1
ML / AI
Probability Functions (Part 1)
ML / AI
Probability Functions (Part 2)
ML / AI
Machine Learning Theory (Part 1)
ML / AI
Machine Learning Theory (Part 2)
ML / AI
KNN Algorithm (Part 1)
ML / AI
KNN Algorithm (Part 2)
ML / AI
Feature scaling
ML / AI
Creating KNN Function
ML / AI
KNN Class specification
ML / AI
Decision Tree (Part 1)
ML / AI
Decision Tree (Part 2)
ML / AI
Fee Rs.20000/-
212 Lectures
Machine Learning
Important Note : Almost all topics have assignments associated with it.
You will get to see code being typed in videos but don't expect us to share the code. We don't share code.
For a good hardworking student, it takes around 18 to 20 months to complete the course.
The topics covered in first 75 lectures are implemented in Python. Then all the remaining implementations are in C and C++.
You will get to see code being typed in videos but don't expect us to share the code. We don't share code.
For a good hardworking student, it takes around 18 to 20 months to complete the course.
The topics covered in first 75 lectures are implemented in Python. Then all the remaining implementations are in C and C++.
Machine Learning / Artificial Intelligence (Course Contents)
- Essential Math
- NumPy Essentials
- Matplotlib Essentials
- SciPy Essentials
- Probability Functions
- Machine Learning - Introduction
- KNN Algorithm - writing function / class
- Feature scaling
- Decision Tree
- Bayes Algorithm
- Pandas
- Classification
- SKLearn IRIS dataset
- Support Vector Machine
- Tensor flow
- Introduction to CUDA Programming
- Introduction to Open CV
- Enough of Python / Lets dive deep
- Using C (Linux) - Deep diving into to core of ML / AI
- Searching Algorithms
- Creating library for math functions
- Creating library for matrix operations
- Expert Systems
- Inference Engine
- Implementing Inference Engine
- Expert System - An Application
- Natural Language Processing
- NLP - Parser
- Removing Noise
- Image Processing
- An Image Processing Application
- Image Processing and AI / ML
- Vision & Pattern Recognition
- Applying filters
- Recognition
- Problem of overlapping objects
- Recognition by classification - Geometric objects
- Program impersonating a human
- ML Functions in OpenCV
- Face detection
- Using C / C++ (Linux) for ML / AI
- Creating Neural Network from scratch
- Exploring C++ ML Libraries
- Image classification - MNIST Dataset
- Neural network - revisited
- PyTorch C++
- Recurrent Neural Network
- Convolutional Neural Network
- NLP Algorithms
- Open Neural Network Exchange Format
- Using Open AI Models for applications
- Using Image Datasets for a applications
- OpenCV for face recognition applications