Machine Learning

Machine Learning 07 – Newton’s Method

In the last couple of blog posts we used Gradient Descent / Gradient Ascent as our optimization algorithm. Gradient Descent works by computing the derivative and then moving in this direction by a small learning rate. There are many optimization algorithms out there. In this post we will learn another one called Newtons Method. The idea Machine Learning 07 – Newton’s Method weiterlesen

Machine Learning 06 – Binary Classification

In this post I will explain how we can use Machine Learning to implement a binary classification algorithm. In binary classification which is also called logistic regression our value can only be 0 or 1. To really get a feeling for what logistic regression means I found it very helpful to look at the definition of Machine Learning 06 – Binary Classification weiterlesen

Machine Learning 05 – Probabilistic Interpretation of Least Squares Method

In this post, we will discuss and show, why the least squares method is actually the way it is. To do this, we have to use Probability theory and some probabilistic assumption on our various variables. Let’s say, that for every data-set in our training data the following rule applies: . While is an error value, which Machine Learning 05 – Probabilistic Interpretation of Least Squares Method weiterlesen

Machine Learning 04 – Locally Weighted Regression

In this blog post I will explain what the Locally Weighted Regression is and when it makes sense to use. Picture the following data set as our given training data. We want to be able to make predictions based on the features, that’s what regression is all about. If we use the feature our prediction Machine Learning 04 – Locally Weighted Regression weiterlesen

Machine Learning 03 – Normal Equation

Last post I explained the math behind and the Gradient Descent algorithm and implemented it in python. This part we will see how to evaluate using a normal equation. We defined  to be half of the sum of the distance between the target values and the prediction squared. We can define some matrices to write down using only Machine Learning 03 – Normal Equation weiterlesen

Machine Learning 02 – Gradient Descent

Linear Regression is the most basic task of Machine Learning. In statistics, linear regression is an approach for modeling the relationship between a scalar dependent variable y and one or more explanatory variables (or independent variables) denoted X. We will use the following training data (they are just made up points): features = [ 3, Machine Learning 02 – Gradient Descent weiterlesen

Machine Learning 01 – Introduction

Machine Learning is a subset of Artificial Intelligence. Computer programs should predict an outcome without beeing explicitly programmed. Supervised Learning We talk about Supervised Learning whenever the machine gets training data to learn from. The machine is „supervised“ by the data. Types of Supervised Learning are Regression and Classification. Regression: A function is determined, which best Machine Learning 01 – Introduction weiterlesen