search query: @keyword deep learning / total: 9
reference: 5 / 9
| Author: | Luketina, Jelena |
| Title: | Hyperparameter Optimization for Machine Learning |
| Publication type: | Master's thesis |
| Publication year: | 2016 |
| Pages: | 73 Language: eng |
| Department/School: | Perustieteiden korkeakoulu |
| Main subject: | Applied and Engineering Mathematics (SCI3016) |
| Supervisor: | Hollanti, Camilla ; Dubashi, Devdatt |
| Instructor: | Raiko, Tapani |
| Electronic version URL: | http://urn.fi/URN:NBN:fi:aalto-201606292835 |
| Location: | P1 Ark Aalto 4207 | Archive |
| Keywords: | hyperparameter machine learning deep learning optimization gradient-based |
| Abstract (eng): | In the recent years, there have been significant developments in the field of machine learning, with the modern methods like deep learning, significantly overpassing previous state-of-the-art results on a variety of tasks. These modern methods however, come at the cost of increased complexity and require careful tuning of multiple hyperparameters which specify the model. The common practice still is manual tuning of the hyperparameters, making the use of deep learning methods, more of an art than a science. In this thesis, we will explore some of the methods for automated hyperparameter optimization, focusing on the gradient-based approach. The goal is to provide a gentle introduction to this topic, by first providing a solid overview of essential concepts from both optimization and machine learning. |
| ED: | 2016-07-17 |
INSSI record number: 54109
+ add basket
INSSI