Introduction to Machine Learning

This repository contains my implementations and/or notes for practice exercises in learning and applying machine learning concepts.

Resources
Course from Linnaeus University :
2DV516 Introduction to Machine Learning, 7.5 credits; Link to course.

Course from Harvard University (OpenCourseWare) / edX:
HarvardX: CS50's Introduction to Artificial Intelligence with Python; Link to course.

Video Content Timestamps from CS50's Playlist

Search

00:00:00 - Introduction
00:00:15 - Artificial Intelligence
00:03:14 - Search
00:14:17 - Solving Search Problems
00:25:57 - Depth First Search
00:28:30 - Breadth First Search
00:54:29 - Greedy Best-First Search
01:05:15 - A* Search
01:12:01 - Adversarial Search
01:14:09 - Minimax
01:36:17 - Alpha-Beta Pruning
01:45:28 - Depth-Limited Minimax

Knowledge

00:00:00 - Introduction
00:00:15 - Knowledge
00:04:52 - Propositional Logic
00:21:47 - Inference
00:40:06 - Knowledge Engineering
01:04:33 - Inference Rules
01:30:31 - Resolution
01:38:25 - First-Order Logic

Uncertainty

00:00:00 - Introduction
00:00:15 - Uncertainty
00:04:52 - Probability
00:09:37 - Conditional Probability
00:17:19 - Random Variables
00:26:28 - Bayes' Rule
00:34:01 - Joint Probability
00:40:13 - Probability Rules
00:49:42 - Bayesian Networks
01:21:00 - Sampling
01:32:58 - Markov Models
01:44:17 - Hidden Markov Models

Optimization

00:00:00 - Introduction
00:00:15 - Optimization
00:01:20 - Local Search
00:07:24 - Hill Climbing
00:29:43 - Simulated Annealing
00:40:43 - Linear Programming
00:51:03 - Constraint Satisfaction
00:59:17 - Node Consistency
01:03:03 - Arc Consistency
01:16:53 - Backtracking Search

Learning

00:00:00 - Introduction
00:00:15 - Machine Learning
00:01:15 - Supervised Learning
00:08:11 - Nearest-Neighbor Classification
00:12:30 - Perceptron Learning
00:33:19 - Support Vector Machines
00:39:31 - Regression
00:42:37 - Loss Functions
00:49:33 - Overfitting
00:55:44 - Regularization
00:59:42 - scikit-learn
01:09:57 - Reinforcement Learning
01:13:02 - Markov Decision Processes
01:19:56 - Q-learning
01:38:54 - Unsupervised Learning
01:40:19 - k-means Clustering

Neural Networks

00:00:00 - Introduction
00:00:15 - Neural Networks
00:05:41 - Activation Functions
00:07:47 - Neural Network Structure
00:16:02 - Gradient Descent
00:30:00 - Multilayer Neural Networks
00:32:58 - Backpropagation
00:36:27 - Overfitting
00:38:52 - TensorFlow
00:53:01 - Computer Vision
00:58:09 - Image Convolution
01:08:18 - Convolutional Neural Networks
01:27:03 - Recurrent Neural Networks

Language

00:00:00 - Natural Language Processing
00:05:19 - Formal Grammars
00:13:19 - n-grams
00:16:56 - Markov Chains
00:19:09 - Naive Bayes
00:31:13 - Word Representation
00:35:40 - word2vec
00:48:38 - Attention
00:54:15 - Transformers
01:03:30 - Artificial Intelligence