Sign in Subscribe

Latest

Dividing numbers into equal buckets or bins through Bucketization

Dividing numbers into equal buckets or bins through Bucketization

A common practice in Reinforcement Learning is to go from a continuous space towards a discrete space. What does this mean? Take for example a range of numbers between $]-3, 3[$, if we want to represent all the numbers that fit in this range as a state then we would

Getting started with Azure Functions

Getting started with Azure Functions

So I wanted to write a function for a customer that would trigger a bot. What I thought would be an easy process, turned out to be a lot of debugging and tuning to get everything working. Which is why I decided to write this post to help others get

Getting started with DotNet Core

Getting started with DotNet Core

I wanted to get started with Machine Learning, but rather than using Tensorflow, I wanted to take a different approach and use ML.NET. Now you might ask yourself: "Why use .NET if you have something such as Tensorflow in Python?". Well, my preference goes towards languages containing

Bellman Equations

Bellman Equations

Summary So what did we learn up until now in our Introduction and Markov Property, Chain, Reward Process and Decision Process posts? Initially we defined our basic concepts: * State: What does our current environment look like? * Action: What action are we taking? * Policy: When taking action $a$ in state $s$

The Markov Property, Chain, Reward Process and Decision Process

The Markov Property, Chain, Reward Process and Decision Process

As seen in the previous article, we now know the general concept of Reinforcement Learning. But how do we actually get towards solving our third challenge: "Temporal Credit Assignment"? To solve this, we first need to introduce a generalization of our reinforcement models. When we look at these

Ordinary Least Squares (OLS)

Ordinary Least Squares (OLS)

Let's start by defining the goal of our algorithm, what do we want to achieve with our OLS algorithm? Well if we have data points in a region (or XY-axis), then we want to be able to find an equation that fits as closely to these points as

Getting AMQP to work in your browser

Getting AMQP to work in your browser

For one of my customers, I had to be able to connect to an EventHub through the browser, so how did I do this? So we know that EventHub works with the AMQP protocol, so what if we could get this working in the frontend? After fiddling a bit with