ML-100days-bootcamp

In this repository,I have submitted some Machine learning projects which i made during learning process starts with the essentials of Python, gradually moving towards to concepts of advanced algorithms and finally into the cores of Machine Learning. With our key focus being the live projects, we dive deeper into the fundamentals of Regression Techniques and Neural Networks enabling the students to work out optimizing solutions to the real-world problems. It is just a matter of weeks before the students actually begin building intelligent systems, working on AI algorithms and data crunching. As a part of these online Machine Learning classes, a detailed overview of the programming fundamentals and Python Basics would be covered with the students so as to make them grasp the concepts of Machine Learning quickly and effortlessly.

Course Contents

The course is broadly divided in 7 categories, each of the topic is present as a section in the course.

Part 1. Introduction to Machine Learning

1. Python Recap
2. Intermediate Python
3. Machine Learning Introduction
4. Data Generation & Visualisation
5. Linear Algebra in Python

Part 2. Supervised Learning Algorithms

• Linear Regression
• Locally Weighted Regression
• Multivariate Regression
• Logistic Regression
• K-Nearest Neighbours
• Naive Bayes
• Support Vector Machines
• Decision Trees & Random Forests

Part 3. Unsupervised Learning

• K-Means
• Principal Component Analysis
• Autoencoders(Deep Learning)
• Generative Adversial Networks(Deep Learning)

Part 4. Deep Learning

• Deep Learning Fundamentals
• Keras Framework, Tensorflow Basics
• Neural Networks Basics
• Building Text & Image Pipelines
• Multilayer Perceptrons
• Optimizers, Loss Functions

Part 5. Deep Learning in Computer Vision

• Convolution Neural Networks
• Image Classification Pipeline
• Alexnet, VGG, Resnet, Inception
• Transfer Learning & Fine Tuning

Part 6. Deep Learning Natural Language Processing

• Sequence Models
• Recurrent Neural Networks
• LSTM Based Models
• Transfer Learning
• Natural Lang Processing
• Word Embeddings
• Langauge Models

Part 7. Reinforcement Learning

• Basics of Reinforcement Learning
• Q Learning
• Building AI for Games

Libraries, Frameworks

• Most of the course codes are build from scratch but we will also teach you how to work with the following libraries.

1. Pandas (Data Handling)
2. Matplotlib (Data Visualisation)
3. Numpy (Maths)
4. Keras (Deep learning)
5. Tensorflow(Introduction)
6. Sci-kit Learn(ML Algorithms)
7. OpenAI Gym (Reinforcement Learning)

Pre-requisites

• Familiar with writing Code in any programming language, Python preferred but not mandatory
• Practical Knowledge of Data Structures, OOP's Concepts
• Familiar with VCS like Git/Github

20 Mini Projects in course!

---

1. Hardwork Pays Off (Regression Prediction)
2. Air Quality Prediction (Multivariate Regression)
3. Separating Chemicals (Logistic Regression)
4. Face Recognition (OpenCV, K-Nearest Neighbours)
5. Handwritten Digits Classifier
6. Naive Bayes Mushroom Classification
7. Movie Review Prediction (Naive Bayes, LSTM etc)
8. Image Dominant Color Extraction (K-Means)
9. Image Classification using SVM
10. Titanic Survivor Prediction using Decision Trees
11. Diabetic Patients Classification
12. Non-Linear Data Separation using MLP
13. Pokemon Classification using CNN, Transfer Learning
14. Sentiment Analysis using MLP, LSTM
15. Text/Lyrics Generation using Markov Chains
16. Emoji Prediction using Transfer Learning & LSTM
17. Odd One Out (Word2Vec)
18. Bollywood Word Analgoies (Word Embeddings)
19. Generating Cartoon Avatars using GAN's (Generative Adversial Networks)
20. Reinforcement Learning based Cartpole Game Player

Final Project

Image Captioning Generating Captions for images using CNN & LSTM on Flickr8K dataset.