Essays about: "Speed-up effect"
Showing result 1 - 5 of 41 essays containing the words Speed-up effect.
-
1. The Impact of Deep Neural Network Pruning on the Hyperparameter Performance Space: An Empirical Study
University essay from Göteborgs universitet/Institutionen för data- och informationsteknikAbstract : With the continued growth of deep learning models in terms of size and computational requirements, the need for efficient models for deployment on resource-constrained devices becomes crucial. Structured pruning has emerged as a proven method to speed up models and reduce computational requirements. READ MORE
-
2. Comparison of properties on Orally Disintegrating Tablets (ODTs) produced by direct compression or fluid bed granulation
University essay from Lunds universitet/Livsmedelsteknik och nutrition (master)Abstract : Orally disintegrating tablets (ODTs) is a popular drug delivery system as they dissolve in the mouth, usually within seconds which enables easy medication for patients with problem swallowing. In this thesis properties of ODTs were compared when produced with direct compression of the excipients or the excipients were pretreated to form granules in a fluid bed granulator prior to tableting. READ MORE
-
3. Diffusion-based Vocoding for Real-Time Text-To-Speech
University essay from Lunds universitet/Matematisk statistikAbstract : The emergence of machine learning based text-to-speech systems have made fully automated customer service voice calls, spoken personal assistants, and the creation of synthetic voices seem well within reach. However, there are still many technical challenges with creating such a system which can generate audio quickly and of high enough quality. READ MORE
-
4. Option pricing with Quadratic Rough Heston Model
University essay from Uppsala universitet/Sannolikhetsteori och kombinatorikAbstract : In this thesis, we study the quadratic rough Heston model and the corresponding simulation methods. We calibrate the model using real-world market data. We compare and implement the three commonly used schemes (Hybrid, Multifactor, and Multifactor hybrid). We calibrate the model using real-world market SPX data. READ MORE
-
5. Neural Network Based Control Design for a Unicycle System
University essay from Linköpings universitet/ReglerteknikAbstract : Physics-based models of dynamical systems can take a lot of time and be hard to derive, and there will always be some effect that was not added to the calculations, like aerodynamic-, gyroscopic- or frictional- effects. Calculating all these effects takes time and a lot of knowledge of the system dynamics. READ MORE