Subject archive for "code"

In a previous blog post we talked about the foundations of reinforcement learning. We covered classical and operant conditioning, rewards, states, and actions, and did a review of some common reinforcement learning use-cases. This entry is a continuation of the series. In it, we present the k-armed bandit problem - a very simple setting that enables us to introduce the interaction between some of the key components of reinforcement learning.

In this article, we will introduce and implement k-nearest neighbours (KNN) as one of the supervised machine learning algorithms. KNN is utilised to solve classification and regression problems. We will provide sufficient background and demonstrate the utility of KNN in solving a classification problem in Python using a freely available dataset.

It’s now normal for computational power to be improved continuously over time. Monthly, or at times even weekly, new devices are being created with better features and increased processing power. However, these enhancements require intensive hardware resources. The question then is, Are you able to use all the computational resources that a device provides? In most cases, the answer is no, and you’ll get an out of memory error. But how can you make use of all the computational resources without changing the underlying architecture of your project?

In this blog post we take a deep dive into the internals of Support Vector Machines. We derive a Linear SVM classifier, explain its advantages, and show what the fitting process looks like when solved via CVXOPT — a convex optimization package for Python.

A picture is worth 1000 words, so let's get right into exploring Domino Code Assist (DCA). As I mentioned in my prior blog, with DCA you can import a dataset, make a few data visualizations, and deploy those data visualizations as a Python data app - all through a point-and-click interface. At the end of this, you have a perfectly executable Python or R script that follows the steps that you took in the UI.