Sökning: "Tolkbarhet"
Visar resultat 1 - 5 av 17 uppsatser innehållade ordet Tolkbarhet.
1. Interpretability and Accuracy in Electricity Price Forecasting : Analysing DNN and LEAR Models in the Nord Pool and EPEX-BE Markets
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Market prices in the liberalized European electricity system play a crucial role in promoting competition, ensuring grid stability, and maximizing profits for market participants. Accurate electricity price forecasting algorithms have, therefore, become increasingly important in this competitive market. LÄS MER
2. Modelling Customer Lifetime Value in the Retail Banking Industry
Kandidat-uppsats, KTH/Matematisk statistikSammanfattning : This thesis was conducted in cooperation with the Swedish bank SEB, who expressed interest in getting an increased understanding of how the marketing measure Customer Lifetime Value could be implemented and used in the retail banking industry. Accordingly, the purpose of this thesis was to provide insight into how Customer Lifetime Value could be modelled in an appropriate way in the retail banking industry and provide an increased understanding of necessary considerations for the modelling process. LÄS MER
3. Explainable Multimodal Fusion
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Recently, there has been a lot of interest in explainable predictions, with new explainability approaches being created for specific data modalities like images and text. However, there is a dearth of understanding and minimal exploration in terms of explainability in the multimodal machine learning domain, where diverse data modalities are fused together in the model. LÄS MER
4. Wavebender GAN : Deep architecture for high-quality and controllable speech synthesis through interpretable features and exchangeable neural synthesizers
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Modeling humans’ speech is a challenging task that originally required a coalition between phoneticians and speech engineers. Yet, the latter, disengaged from phoneticians, have strived for evermore natural speech synthesis in the absence of an awareness of speech modelling due to data- driven and ever-growing deep learning models. LÄS MER
5. Are deep video architectures (also) biased toward texture rather than shape?
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Convolutional neural networks (CNNs) have achieved high accuracy on several different perceptual tasks, such as object recognition and action recognition. Interpretability is required due to the significant impact of CNNs and the requirement of model improvement. Geirhos et al. LÄS MER