Machine Learning From Scratch

Overview

• Focus on Commonly used Machine Learning algorithms and models
• Implemented in python using some common datasets such as iris, Admission_predict
• Built from sctratch using general libraries like NumPy, Pandas, math (no ML libraries)

List of Models

• Linear Regression (Least square method)
• Linear Regression (using Gradient Descent Optimizer)
• Logistic Regression (using Gradient Descent Optimizer)
• Local weighted Regression
• sylvester criterion
• Random Network

Introduction

Machine Learning (ML) is a subfield of Artificial Intelligence. It is widely used to understand the pattern of data and its behavior. The main objective of ML models is to automatically learn and improve from experience without being explicitly programmed.

The term Machine Learning was introduced by Arthur Samuel in 1959. He was an American pioneer in the field of computer gaming and artificial intelligence. He stated

“it gives computers the ability to learn without being explicitly programmed”

Machine Learning Paradigms

• Supervised Learning: ML models, in supervised learning, uses the training data to train the model. It fits the model by learning from various samples of the features and its responses. Then the model is used to predict the response for a new data sample. The most common examples are Linear Regression, Logistic Regression and Support Vector Machine(SVM).
• Unsupervised learning: The model learns from the dataset without any labeled responses. The most common example of Unsupervised learning is clustering, which is used for exploratory data analysis to find hidden patterns or grouping in data.
• Reinforcement learning: Reinforcement learning is another paradigm of ML, concerned with how software agents ought to take actions in an environment in order to maximize the notion of cumulative reward.