Sökning: "learning problems in mathematics"
Visar resultat 16 - 20 av 80 avhandlingar innehållade orden learning problems in mathematics.
16. ”Vad skulle x kunna vara?” : andragradsekvation och andragradsfunktion som objekt för lärande
Sammanfattning : Algebraic equations and functions play an important role in various mathematical topics, including algebra, trigonometry, linear programming and calculus. Accordingly, various documents, such as the most recent Swedish curriculum (Lpf 94) for upper secondary school and the course syllabi in mathematics, specify what the students should learn in Mathematics Course B. LÄS MER
17. Accelerating Monte Carlo methods for Bayesian inference in dynamical models
Sammanfattning : Making decisions and predictions from noisy observations are two important and challenging problems in many areas of society. Some examples of applications are recommendation systems for online shopping and streaming services, connecting genes with certain diseases and modelling climate change. LÄS MER
18. Learning with Geometric Embeddings of Graphs
Sammanfattning : Graphs are natural representations of problems and data in many fields. For example, in computational biology, interaction networks model the functional relationships between genes in living organisms; in the social sciences, graphs are used to represent friendships and business relations among people; in chemoinformatics, graphs represent atoms and molecular bonds. LÄS MER
19. Causal Combinatorics : Edges of the Characteristic Imset Polytopes
Sammanfattning : Explaining data in a concise and efficient manner has become increasingly important in today's society. This thesis pertains to the problem of finding causal links within data, and how that can be done from a mathematical perspective. Using the framework of graphical models has several advantages, from interpretability to efficiency. LÄS MER
20. G-equivariant convolutional neural networks
Sammanfattning : Over the past decade, deep learning has revolutionized industry and academic research. Neural networks have been used to solve a multitude of previously unsolved problems and to significantly improve the state-of-the-art on other tasks, in some cases reaching superhuman levels of performance. LÄS MER