Sökning: "fine tuning"
Visar resultat 6 - 10 av 226 uppsatser innehållade orden fine tuning.
6. The Impact of Deep Neural Network Pruning on the Hyperparameter Performance Space: An Empirical Study
Master-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknikSammanfattning : With the continued growth of deep learning models in terms of size and computational requirements, the need for efficient models for deployment on resource-constrained devices becomes crucial. Structured pruning has emerged as a proven method to speed up models and reduce computational requirements. LÄS MER
7. Evaluating and optimizing Transformer models for predicting chemical reactions
Master-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknikSammanfattning : In this thesis, we assess the effectiveness of a transformer model specifically trained to predict chemical reactions. The model, named Chemformer, is a sequence-tosequence model that uses the transformer’s encoder and decoder stacks. LÄS MER
8. Natural Language Inference Transfer Learning in a Multi-Task Contract Dataset : In the Case of ContractNLI: a Document Information Extraction System
Master-uppsats, Uppsala universitet/Institutionen för lingvistik och filologiSammanfattning : This thesis investigates the enhancement of legal contract Natural Language Inference (NLI) classification through supervised fine-tuning on general domain NLI, in the case of ContractNLI and Span NLI BERT (Koreeda and Manning, 2021), a multi-task document information extraction dataset and framework. Annotated datasets of a specific professional domain are scarce due to the high time and labour cost required to create them. LÄS MER
9. Development and Implementation of Techniques for the Simulation and Processing for Future SAR Systems
Master-uppsats, Luleå tekniska universitet/Institutionen för system- och rymdteknikSammanfattning : Synthetic Aperture Radar (SAR) is a type of radar system that can generate high-resolution images with which one can detect subtle changes on the scale of centimetres from space. It can operate in any weather condition and during both day and night, making it unique compared to optical sensors. LÄS MER
10. Assessing the Efficiency of COLMAP, DROID-SLAM, and NeRF-SLAM in 3D Road Scene Reconstruction
Master-uppsats, Lunds universitet/Matematik LTHSammanfattning : 3D reconstruction is a field in computer vision which has evolved rapidly as a result of the recent advancements in deep learning. As 3D reconstruction pipelines now can run in real-time, this has opened up new possibilities for teams developing Advanced Driver Assistance Systems (ADAS), which rely on the camera system of the vehicle to enhance the safety and driving experience. LÄS MER