Interpretable Deep Learning falls into the category of Artificial Intelligence and is particularly important for areas such as automation and digital transformation. Deep Learning describes a form of machine learning where computers learn independently from large amounts of data. However, it often remains unclear precisely how a computer arrives at its decisions – this is known as a „black box“.
Interpretable deep learning means that we can understand why an algorithm makes a particular decision. This is very important in medicine, for example: if an artificial intelligence detects cancer in an image, doctors want to understand which features in the image played a decisive role. Interpretable deep learning can make such decision pathways visible, for instance, through coloured markings in the image.
This increases trust in the technology and allows errors to be identified more effectively. At the same time, interpretable deep learning helps companies make transparent decisions – for example, in the automated selection of job applicants in HR. In summary, it helps us to better understand and responsibly deploy artificial intelligence.
Deutsch 
English (UK)