Blog

For some weeks, I have been building the foundations of what I dream to become an AI App store: seeme.ai The Goal Easily build, consume and share world-class AI models via the web, Docker, an api or the SeeMe mobile app. 1. Build Build your own world-class models for your own private/internal use. 2. Consume Our AI store will host a range of useful models you can easily integrate. 3. Share Share your AI models with the world for fun and profit in the Seeme AI Store.

TL;DR seeme.ai - create your own image classifier without a single line of code. A deep learning experiment A few days ago, I started experimenting with automating computer vision with deep learning as much as I could. I want people to be able to create their own image classifiers, but without: the need to find lots of images; knowing anything about deep learning or AI. It is a long way from being generally usable, but there is no smoke and mirrors involved.

[Update April 15, 2019] This blog post covers the 2018 course which you can find here. TL;DR The first lesson gives an introduction into the why and how of the fast.ai course, and you will learn the basics of Jupyter Notebooks and how to use the fast.ai library to build a world-class image classifier in three lines of Python. You will get a feel for what deep learning is and why it works, as well as possible applications you can build yourself.

[Update April 15, 2019] This blog post covers the 2018 course which you can find here. (Copyright fast.ai) Most approaches teaching machine and deep learning can be cumbersome and time-consuming: Stepping through all the details of (basic) linear algebra, activation functions and slowly building a neural network, so that after a few weeks/months, you are able to build an image classifier, if you have actually powered through… Do not get me wrong, understanding the intuition and fundamentals of linear algebra and neural networks are an important and invaluable asset in achieving great results.

Photo by Jonathan Velasquez on Unsplash 0. Introduction I listen to a lot of podcasts while running or in the car and a great deal of those are related to machine learning and artificial intelligence, each providing their own take on the subjects. Whether you are new or experienced, a practioner or just interested in real-world applications, there is probably a podcast that suites your needs and interests. In this blog post, I have listed the podcasts that I listen to on a regular basis, described what they are about and added my favorite episode.

It seems I am spending more and more of my days in Jupyter Notebooks lately. While still following the fast.ai course - sometimes life gets in the way of your plans - I noticed datasets are either included or there is a link to a .zip file, which you still need to download and extract by hand. After some manual repetitions, I started dabbling with a small script to make that part easier, so I could just focus on running experiments in the future.