DEFENCE OF THE DOCTORAL DISSERTATION BY JAKOB JELENČIČ

Smart denoising for recurrent neural networks optimization

Defence of the Doctoral Dissertation by Jakob Jelenčič

Published: 25. nov. 2024

IPS invites you to the Defence of the Doctoral Dissertation by Jakob Jelenčič titled: Smart denoising for recurrent neural networks optimization. The defence will take place on Thursday, 28 November 2024, at 9:30 a.m. at the IPS Lecture Room, Jamova 39, 1000 Ljubljana. You can also join the defence via the following link: https://us02web.zoom.us/j/84614651252?pwd=wMyFfoS58TKRF6uiyx2mpufL01ffFz.1, Meeting ID: 846 1465 1252, Passcode: 471193.

Short summary:

This thesis introduces a new optimization method based on deep learning, designed for data influenced by random processes. The main contribution of this method is the combination of advanced noise reduction techniques with recurrent neural network models, which helps to prevent the common problem of overfitting seen when there is not much training data available. This approach greatly improves how the model optimizes data representation and target outcomes, and enhances the model's performance by managing noise effectively.

Back to all news