When working on machine learning problems I find that productivity is sometimes somewhat low, because I have to spend a lot of time working on tedious bits that probably can be automated away. Over time I have found quite a few tools that help me get better results faster. Here's three of them.
Read moreMicrosoft now offers a new MCSA certification for people that want to expand into the world of machine learning. Here's a run down of the exams and what you will need to learn to earn this certification.
Read moreHow do you start with AI when you're a developer and have no idea where to begin? Organize a workshop for your colleagues and challenge them to start exploring machine learning. I certainly learned a ton while organizing the AI learning experience. It was a lot of fun.
Read moreI've embarked on my hardest and most fun adventure ever. I'm going to implement my own deep learning framework. I know most people will call me crazy. But I think this is a challenge that was long coming and I finally got around to it. Wonder why? Read on.
Read moreBot 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.
Read moreWhen 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.
Read moreDiscover how you can use Cognitive Toolkit to bring your models to production with Python and Java.
Read moreCurrently 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 good alternative yet. I
Read moreWhen 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.
Read moreMicrosoft 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.
Read moreYou 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.
Read moreSetting 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.
Read more