Image classification models are intended to classify images into classes. We usually want to divide them into groups that reflect what objects are on a picture. For example, we can train an image classification model that can distinguish "dog" from "cat," but of course, even more complex classifications can be made in significantly more classes.
Deep learning is now often considered to be the "holy grail" when it comes to developing intelligent systems. While fully automatic and autonomous machine learning is on the way, current solutions still require the understanding of a software developer or engineer. Deep learning, by contrast, is a sub-discipline of machine learning that promises deep-reaching learning success without human intervention and is oriented towards the function and operation of neural networks in the human brain.
You already have some experience with SQL and are wondering how you could find solutions to problems in R? Then this article is just the thing you need! We’ll start with the basic elements of the language - with lots of specific sample code to help. Then we’ll take a look at how we can deal with data (this is where basic SQL skills are helpful, but not required). And last but not least, we'll look at use cases that can typically be solved with R.
When Guido van Rossum developed Python, he wanted to create a "simple" programming language that bypassed the vulnerabilities of other systems. Due to the simple syntax and sophisticated syntactic phrases, the language has become the standard for various scientific applications such as machine learning.
It is well-known in the Developer Scene that there is no better machine learning language than Python. One of the reasons why this programming language is so popular is the fact that it has a huge collection of great libraries, that makes the life of a developer a lot easier.
How can AI be turned into a commodity – a cheap, easily available product, that is used by everyone? Will it even be possible to turn AI into a commodity at all? Dr. Pieter Buteneers (Robovision) adresses these questions in this keynote from ML Conference 2018 in Berlin.
If you cannot or do not want to build an AI project from scratch, you have countless choices of ready-made services. But what can you do if the finished services do not fit the project? Customizable AI and ML models in the cloud, which you can train with your own data, provide a remedy.
The cold start problem affects both startups as well as established companies. Nonetheless, it also provides a great opportunity to collect new data with your customer’s problem in focus. How do you solve the cold start problem and arrive at a useful data pipeline? We talked to ML Conference speakers Markus Nutz and Thomas Pawlitzki about all this and more.
Machine learning may have all sorts of use cases, but forecasting? In honor of the upcoming ML Conference, we talked to Philipp Beer about how data scientists can utilize ML in statistical forecasting. We talk about the advantages and disadvantages of modern vs. classical methods, how can one decide between the two, and where should they turn when they need good predictions for their business KPIs.