Sökning: "inherently interpretable"
Hittade 3 uppsatser innehållade orden inherently interpretable.
1. Developing a highly accurate, locally interpretable neural network for medical image analysis
Master-uppsats, Stockholms universitet/Institutionen för data- och systemvetenskapSammanfattning : Background Machine learning techniques, such as convolutional networks, have shown promise in medical image analysis, including the detection of pediatric pneumonia. However, the interpretability of these models is often lacking, compromising their trustworthiness and acceptance in medical applications. LÄS MER
2. Sequential Deep Learning Models for Neonatal Sepsis Detection : A suitability assessment of deep learning models for event detection in physiological data
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Sepsis is a life-threatening condition that neonatal patients are especially susceptible to. Fortunately, improved bedside monitoring has enabled the collection and use of continuous vital signs data for the purpose of detecting conditions such as sepsis. LÄS MER
3. Explaining the output of a black box model and a white box model: an illustrative comparison
Kandidat-uppsats, Uppsala universitet/Filosofiska institutionenSammanfattning : The thesis investigates how one should determine the appropriate transparency of an information processing system from a receiver perspective. Research in the past has suggested that the model should be maximally transparent for what is labeled as ”high stake decisions”. LÄS MER