Willem's Fizzy Logic

Learn how to build a bot with the new Microsoft Bot Builder Java SDK

Bot builder from Microsoft has been around for a couple of years now. During Microsoft Build 2018 a preview of version 4.0 was launched with support for more languages. Previously you could only build a bot in C# or Node. Now you can build one in Java too. Here's how.

Machine Learning

Learn how automatically tag images with the Computer Vision API

When you're not into building your own machine learning models or neural networks, but still want to do something with AI to recognize images, then Microsoft has you covered with the Computer Vision API as part of their Cognitive Services. Wonder how to use it? Learn it here.

Machine Learning

Bring your deep learning models to production with CNTK on Java

Discover how you can use Cognitive Toolkit to bring your models to production with Python and Java.

Time to do it differently, build chatbots with streams

Currently when you want to build a chat bot in Microsoft Bot Builder you have to deal with the rather complicated dialog system. I really don't like it, but there isn't a very

Machine Learning

Learn how to visualize your CNTK based neural network

When you're building complex neural networks you often want to visualize them. Visualization offers a great way to debug things like performance bottlenecks, because parts of your network get duplicated by CNTK. Luckely, it is quite easy to visualize a neural network in CNTK. Here's how.

Machine Learning

Here's why Microsoft Cognitive Toolkit is the coolest deep learning framework around

Microsoft cognitive toolkit supports loading and saving models in ONNX format, which enables you as a developer to run your trained network on Java and C# with much better overall performance than you can get with Python.

Machine Learning

Adventures in AI part 3: How do I know my ML model is any good?

You can train any model you like for your AI solution, but it is only as good as the data you feed it. But how do you measure the performance of a machine learning model? In this third part of the series on AI models I will show you how.

My python setup on Windows 10

Setting up a proper development environment for Python and Data Science projects can be hard on Windows. Python's origin isn't on Windows which shows, but you can get it to work with just a few tweaks. Here's how.

How to quickly build a REST API in Django

Vacation time, an excellent time to learn something new, so I figured, why not build a recipe bot that recommends recipes? For that I needed a way to store recipes that the bot could retrieve. And I figured, why not try to build that in Python with Django?

Machine Learning

How-to: run Microsoft Cognitive Toolkit based application inside a Docker image

As part of a Community Hack at Microsoft Denmark people can hack together basic AI models with CNTK. Two fellow MVPs asked me if they could use Docker to work on CNTK applications.

Machine Learning

Embedded AI: The Nvidia Jetson TX1 - Part 1

Every once in a while you run across something that you just have to have. I bumped into a cool little device, the Nvidia Jetson TX1. This is a creditcard size AI computer that looks to be fun. So I had to try it.

Machine Learning

Learn how to build flexible machine learning pipelines in scikit-learn

Setting up a machine learning algorithm involves more than the algorithm itself. You need to preprocess the data in order for it to fit the algorithm. It's this preprocessing pipeline that often requires a lot of work. Building a flexible pipeline is key. Here's how you can build it in python.

5 easy steps to start editing python notebooks over SSH

When you work with Linux machines on Amazon EC2 or Azure over SSH and want to edit interactive python code you've got a challenge. There is vim and other console based editors, but that might not be what you want. Here's how you can edit python code in your browser over SSH in 4 steps.

How to setup tox on Windows with Anaconda

When you are developing packages for Python you need some way to test whether your package works on someone else's computer. Tox is a great tool for this, but doesn't work well with Anaconda. With some basic steps however you can have your code tested on tox without much trouble.

Machine Learning

Machine learning tips: How to quickly generate a bag of words

Natural language processing is all about text. But it doesn't use the text itself. You need vectors of numbers, for example a bag of words. This can be easily built with a dictionary and some for loops. But there is an easier way.

Run Rider even with the new .NET Core 2.0 SDK

This week .NET Core 2.0 alongside with ASP.NET Core 2.0 was released. A lot of improvements were made to the runtime and the size of the standard libraries has increased

Machine Learning

Which celebrity are you? A celebrity scanner built with Clarifai

When it comes to building solutions with AI you want to be smart. Don't just run in there and start using Tensorflow. There are many good solutions such as Clarifai out there that don't require a lot of work, but still produce superior results.

How to generate PDF documents in ASP.NET Core

A customer I work for wants to generate a set of attachments for an e-mail we need to send to the clients of that customer. We ended up using DinkToPdf with the ASP.NET Core Razor Template Engine to build a PDF generation microservice.

Machine Learning

Adventures in AI Part 2: Which algorithm should I use?

Choosing the right algorithm for your machine learning problem can be quite hard. I've had numerous questions about it during the machine learning course. Also I've seen many people struggle to find more

How to connect Azure API management to your Kubernetes cluster

For a customer I'm working on a new cloud architecture that will help them move to production quicker. The goal for our team is to setup a working product, but at the same

Machine Learning

Adventures in AI part 1: What is a gradient descent algorithm?

When you start out with machine learning and AI you will learn very quickly that there's a lot of math involved. All this math is very hard to understand, especially if you have

Machine Learning

Monitor progress of your Keras based neural network using Tensorboard

In the past few weeks I've been breaking my brain over a way to automatically answer questions using a neural network. I have a working version, but debugging a neural network is a

Machine Learning

Machine learning ideas: Anomaly detection

Machine Learning ideas: Anomaly detection using K-Means From time to time I come across Machine Learning ideas. As I come across them I like to explain them to you my reader and encourage

Machine Learning

A modern stack for data analysis in a microservice world

The face of enterprise solutions is changing rapidly. We are making smaller solutions at a larger scale by deploying microservice architectures. This brings many advantages to developers and customers because solutions become more

Machine Learning

How-to: Experiment with tensorflow in an interactive notebook

I've always wanted to build something with tensorflow. I have one demo lying around with tensorflow, but never got around to develop something for real with this framework. Although tensorflow has a lot