Essays about: "model order reduction using deep learning"
Found 3 essays containing the words model order reduction using deep learning.
-
1. Improving the Robustness of Deep Neural Networks against Adversarial Examples via Adversarial Training with Maximal Coding Rate Reduction
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : Deep learning is one of the hottest scientific topics at the moment. Deep convolutional networks can solve various complex tasks in the field of image processing. However, adversarial attacks have been shown to have the ability of fooling deep learning models. READ MORE
-
2. A Hardware Accelerated Low Power DSP for Recurrent Neural Networks
University essay from Lunds universitet/Institutionen för elektro- och informationsteknikAbstract : Recurrent neural networks (RNNs) have become a dominating player for processing of sequential data such as speech and audio. The reason for this, is the high accuracy that can be achieved with the more complex variants, such as the gated recurrent unit (GRU). READ MORE
-
3. Reduced Order Modelling using Dynamic Mode Decomposition and Koopman Spectral Analysis with Deep Learning
University essay from Lunds universitet/Matematik LTHAbstract : In the industry simulation models are commonly used in system development. These models can become complicated in order to capture the physical behaviour of the underlying dynamical system. A high-fidelity representation, which can result in long simulation times, is in some settings not strictly required. READ MORE