Author: Johannes Wilhelm
-
Efficient Neural Greeks: Directional Sobolev Training via Randomized Hessian Sketching – Master’s Thesis
Algorithmic Differentiation Differential Machine Learning Quantitative Finance RandNLA Sobolev Training Surrogate ModelingThis page provides a brief overview of my Master’s thesis written at RWTH Aachen. The full Thesis is available as… more
-
Non-Uniform Time Resolution for Improved Bitcoin Time Series Predictions
In the first part of this series, I discussed different preprocessing techniques for Bitcoin financial data. We built labeled pricing… more
-
Combining User- and Device-Perspective Rendering for Intuitive Handheld AR – Bachelor’s Thesis
This page provides a brief, high-level overview of my Bachelor’s thesis written at RWTH Aachen. While this page focuses on… more
-
Comparing Preprocessing Approaches for Bitcoin Time Series Prediction
This article is the first part of a series on time-series forecasting for cryptocurrency financial data. This article focuses on… more