Comparison of numerical properties comparing Automated Derivatives (Autograd) and explicit derivatives (Gradients) for Prototype based models
- Differentiation is ubiquitous in the field of mathematics and especially in the field of Machine learning for calculations in gradient-based models. Calculating gradients might be complex and require handling multiple variables. Supervised Learning Vector Quantization models, which are used for classification tasks, also use the Stochastic Gradient Descent method for optimizing their cost functions. There are various methods to calculate these gradients or derivatives, namely Manual Differentiation, Numeric Differentiation, Symbolic Differentiation, and Automatic Differentiation. In this thesis, we evaluate each of the methods mentioned earlier for calculating derivatives and also compare the use of these methods for the variants of Generalized Learning Vector Quantization algorithms.
Author: | Venkata Sai Sandeep Yendamuri |
---|---|
Advisor: | Thomas Villmann, Alexander Engelsberger |
Document Type: | Master's Thesis |
Language: | English |
Year of Completion: | 2022 |
Granting Institution: | Hochschule Mittweida |
Release Date: | 2023/02/06 |
GND Keyword: | Maschinelles Lernen |
Page Number: | 49 |
Institutes: | Angewandte Computer‐ und Biowissenschaften |
DDC classes: | 006.31 Maschinelles Lernen |
Open Access: | Frei zugänglich |
Licence (German): | Urheberrechtlich geschützt |