Sökning: "matematisk idé"
Visar resultat 1 - 5 av 11 uppsatser innehållade orden matematisk idé.
1. Basil-GAN
Master-uppsats, KTH/Matematisk statistikSammanfattning : Developments in computer vision has sought to design deep neural networks which trained on a large set of images are able to generate high quality artificial images which share semantic qualities with the original image set. A pivotal shift was made with the introduction of the generative adversarial network (GAN) by Goodfellow et al.. LÄS MER
2. Muntliga uppgifter för elever med matematisk fallenhet : En granskning av muntliga uppgifter för årskurs 6
Magister-uppsats, Linnéuniversitetet/Institutionen för matematik (MA)Sammanfattning : Studien är en granskning av ett frisläppt nationellt delprov i matematik och ett läromedel för årskurs 6. Uppgifterna som granskas är muntliga uppgifter där eleverna ska diskutera och resonera. LÄS MER
3. Deep Learning Approach to Material Properties
Kandidat-uppsats, Lunds universitet/Matematisk fysik; Lunds universitet/Fysiska institutionenSammanfattning : In this thesis, we consider a deep learning approach to predict material properties. Primarily we study artificial neural networks (ANN), which predict the energy distance to the convex hull (measure of stability) of perovskites. Further, we explore if the networks can be generalised to predict band gaps and unit cell volume. LÄS MER
4. A study and further development of nonlinear unsupervised methods : With applications to financial data
Master-uppsats, KTH/Matematisk statistikSammanfattning : The main focus for this thesis is nonlinear dimensionality reduction. When analysing data of high dimension it is often vital to find a lower dimension representation of the data, while preserving as much information as possible. Dimension reduction is therefore used in many fields of science and in many industries. LÄS MER
5. Latent Task Embeddings forFew-Shot Function Approximation
Master-uppsats, KTH/Optimeringslära och systemteoriSammanfattning : Approximating a function from a few data points is of great importance in fields where data is scarce, like, for example, in robotics applications. Recently, scalable and expressive parametric models like deep neural networks have demonstrated superior performance on a wide variety of function approximation tasks when plenty of data is available –however, these methods tend to perform considerably worse in low-data regimes which calls for alternative approaches. LÄS MER