Essays about: "djup inlärning"
Showing result 21 - 25 of 49 essays containing the words djup inlärning.
-
21. Quality Control of Concrete Piles Based on Historical Data : Machine learning of concrete piles production line
University essay from Karlstads universitetAbstract : This master thesis investigates the parameters influencing the quality of concrete piles produced by NCC in Sweden. Furthermore, the thesis provides an in-depth review of the production and existing issues associated with concrete pile production. READ MORE
-
22. Batch Active Learning for Deep Object Detection in Videos
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : Relatively recent progress in object detection can mainly be attributed to the success of deep neural networks. However, training such models requires large amounts of annotated data. This poses a two-fold problem, namely obtaining labelled data is a time-consuming process, and training models on many instances is computationally costly. READ MORE
-
23. Normalization of Deep and Shallow CNNs tasked with Medical 3D PET-scans : Analysis of technique applicability
University essay from Högskolan i Halmstad/Akademin för informationsteknologiAbstract : There has in recent years been interdisciplinary research on utilizing machine learning for detecting and classifying neurodegenerative disorders with the sole goal of outperforming state-of-the-art models in terms of metrics such as accuracy, specificity, and sensitivity. Specifically, these studies have been conducted using existing networks on ”novel” methods of pre-processing data or by developing new convolutional neural networks. READ MORE
-
24. Multiparty adversarial neural cryptography with symmetric and asymmetric encryption
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : Deep learning has shown excellent performance in image recognition, speech recognition, natural language processing and other fields over the recent decades. Cryptography is a technical science that studies the preparation and decoding of ciphers. READ MORE
-
25. Uncertainty Estimation in Deep Neural Object Detectors for Autonomous Driving
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : One of the most challenging problems in autonomous driving, and in computer vision in general, is the task of object detection. Recently, the advances of deep learning in the domain of computer vision have led the research community to apply ideas from deep learning to the problem of object detection. READ MORE