Essays about: "Förklaringsbar maskininlärning"
Found 4 essays containing the words Förklaringsbar maskininlärning.
-
1. Explainable Machine Learning for Lead Time Prediction : A Case Study on Explainability Methods and Benefits in the Pharmaceutical Industry
University essay from KTH/Hållbar produktionsutveckling (ML)Abstract : Artificial Intelligence (AI) has proven to be highly suitable for a wide range of problems in manufacturing environments, including the prediction of lead times. Most of these solutions are based on ”black-box” algorithms, which hinder practitioners to understand the prediction process. READ MORE
-
2. Investigating the Use of Deep Learning Models for Transactional Underwriting
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : Tabular data is the most common form of data, and is abundant throughout crucial industries, such as banks, hospitals and insurance companies. Albeit, deep learning research has largely been dominated by applications to homogeneous data, e.g. images or natural language. READ MORE
-
3. Exploring attribution methods explaining atrial fibrillation predictions from sinus ECGs : Attributions in Scale, Time and Frequency
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : Deep Learning models are ubiquitous in machine learning. They offer state-of- the-art performance on tasks ranging from natural language processing to image classification. The drawback of these complex models is their black box nature. It is difficult for the end-user to understand how a model arrives at its prediction from the input. READ MORE
-
4. Leveraging Explainable Machine Learning to Raise Awareness among Preadolescents about Gender Bias in Supervised Learning
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : Machine learning systems have become ubiquitous into our society. This has raised concerns about the potential discrimination that these systems might exert due to unconscious bias present in the data, for example regarding gender and race. READ MORE