Sökning: "end-to-end learning"
Visar resultat 26 - 30 av 35 avhandlingar innehållade orden end-to-end learning.
26. Towards Radio-Environment Aware IoT Networks : Wireless Coexistence Methods for Low-complexity Devices
Sammanfattning : Wireless technologies for short-range communication play a central role in the massive diffusion of the Internet of Things (IoT) paradigm. Such communication solutions rely extensively on the availability of unlicensed spectrum in the form of bands for industrial, scientific, and medical (ISM) applications. LÄS MER
27. Resource efficient automatic segmentation of medical images
Sammanfattning : Cancer is one of the leading causes of death worldwide. In 2020, there were around 10 million cancer deaths and nearly 20 million new cancer cases in the world. Radiation therapy is essential in cancer treatments because half of the cancer patients receive radiation therapy at some point. LÄS MER
28. Online Combinatorial Optimization under Bandit Feedback
Sammanfattning : Multi-Armed Bandits (MAB) constitute the most fundamental model for sequential decision making problems with an exploration vs. exploitation trade-off. In such problems, the decision maker selects an arm in each round and observes a realization of the corresponding unknown reward distribution. LÄS MER
29. Life of a Security Middlebox : Challenges with Emerging Protocols and Technologies
Sammanfattning : The Internet of today has intermediary devices known as middleboxes that perform more functions than the normal packet forwarding function of a router. Security middleboxes are a subset of these middleboxes and face an increasingly difficult task to perform their functions correctly. LÄS MER
30. Natural Language Processing for Low-resourced Code-switched Colloquial Languages – The Case of Algerian Language
Sammanfattning : In this thesis we explore to what extent deep neural networks (DNNs), trained end-to-end, can be used to perform natural language processing tasks for code-switched colloquial languages lacking both large automated data and processing tools, for instance tokenisers, morpho-syntactic and semantic parsers, etc. We opt for an end-to-end learning approach because this kind of data is hard to control due to its high orthographic and linguistic variability. LÄS MER