{"id":50856,"date":"2024-01-18T13:26:02","date_gmt":"2024-01-18T12:26:02","guid":{"rendered":"https:\/\/www.accompio.com\/blog\/testen-von-kuenstlicher-intelligenz\/"},"modified":"2026-03-10T07:17:52","modified_gmt":"2026-03-10T06:17:52","slug":"testing-of-artificial-intelligence","status":"publish","type":"blog","link":"https:\/\/www.accompio.com\/en\/blog\/testen-von-kuenstlicher-intelligenz\/","title":{"rendered":"Testing artificial intelligence"},"content":{"rendered":"

Artificial intelligence (AI) is on everyone's lips these days<\/strong> and is often mentioned in the context of more efficient and faster working. Nevertheless, systems like ChatGPT are often criticised. Answers are said to be false, questions are not answered due to restrictive filters, or facts are invented \u2013 the AI creates its own reality.<\/p>\n\n\n\n

In the software industry, ensuring quality and functionality plays an important role. Errors should be found and rectified quickly, ideally before the product even reaches the end customer. This requires thorough software testing. But does this also work with AI? Can AI systems be tested and if so, how? <\/strong>In this blog series, I'll be exploring these questions and reporting on my findings on the subject of \u201eTesting AI\u201c.<\/p>\n\n\n\n

Every beginning is\u2026 surprisingly intuitive?<\/h3>\n\n\n\n

Getting started in the world of AI wasn't exactly easy due to the variety of systems and focuses. I hadn't had much exposure to the topic until now. My experience has so far been limited to generating images with \u201eMidjourney\u201c<\/em>, simple chatbot interactions with \u201eChatGPT\u201c<\/em> and the use of \u201eGoogle Translate\u201c<\/em> for translating texts. So, where's the best place to start and where do you set your own boundaries?<\/strong> The danger is great of quickly getting lost in topics that sound very interesting but take a lot of time to reach the goal.<\/p>\n\n\n\n

First, it was necessary to build a basic understanding of how AI systems work and to deepen this knowledge step by step. The first port of call for this was the \u201eTeachable Machine\u201c<\/em>, with which you can create your own AI for image classification.<\/strong> It even worked surprisingly easily and very intuitively, even without in-depth mathematical knowledge. All it took was holding an object up to the camera of a smartphone or laptop and taking various pictures of the objects at the press of a button on the web interface. With a separate training set for pens, a coffee cup, and headphones respectively, the AI could then distinguish between the objects in real-time, which I just had to hold up to the camera.<\/p>\n\n\n\n

The aim of machine learning is to recognise meaningful relationships within input data and derive rules from them. With these rules, a system can then recognise trends, classify data or make predictions when new, unknown data is input. For example, in the Teachable Machine, an upside-down coffee cup is still classified correctly, even though it no longer matches the data with which the system was originally trained.<\/p>\n\n\n\n

\"Classification\n
Classification in Machine Learning (Image: accompio PrimeTec GmbH)<\/em><\/figcaption>\n<\/figure>\n\n\n\n

After the initial experiments with the image classification AI already delivered promising and, above all, very clear results, The next item on the agenda is to implement a similar system on our own machine.<\/strong>. Fortunately, the developers of Teachable Machine had an older version of the system open-source on GitHub<\/a> published. Even though it's the archived original version and the functions are quite basic, a look into the program code was quite insightful. For example, the images are trained locally on the machine using Tensorflow. There is no communication with other services.\u00a0<\/p>\n\n\n\n

\"Workflow\n
The first version of \u201dTeachable Machine\u201d reliably recognises the blue pen, which is labelled as the \u201dpurple\u201d class.<\/em><\/figcaption>\n<\/figure>\n\n\n\n

Image Classification \u2013 What needs to be considered?\u00a0<\/h3>\n\n\n\n

The system is up and running and is already delivering initial results. In tests, the AI is up to 95 percent certain that the recognised object is indeed the one shown. However, in other cases, the objects are misclassified. A coffee cup suddenly becomes a pen, and in another instance, the AI can no longer distinguish between the items. How can this happen?\u00a0
\u00a0
During the creation of the training data, some important characteristics have emerged:\u00a0<\/strong><\/p>\n\n\n\n