Sökning: "fine-tuning"
Visar resultat 1 - 5 av 216 uppsatser innehållade ordet fine-tuning.
1. En undersökning av metoder förautomatiserad text ochparameterextraktion frånPDF-dokument med NaturalLanguage Processing
M1-uppsats, KTH/Hälsoinformatik och logistikSammanfattning : I dagens affärsmiljö strävar många organisationer efter att automatisera processen för att hämta information från fakturor. Målet är att göra hanteringen av stora mängder fakturor mer effektiv. Trots detta möter man utmaningar på grund av den varierande strukturen hos fakturor. LÄS MER
2. AI-based image generation: The impact of fine-tuning on fake image detection
Kandidat-uppsats, Stockholms universitet/Institutionen för data- och systemvetenskapSammanfattning : Machine learning-based image generation models such as Stable Diffusion are now capable of generating synthetic images that are difficult to distinguish from real images, which gives rise to a number of legal and ethical concerns. As a potential measure of mitigation, it is possible to train neural networks to detect the digital artifacts present in the images synthesized by many generative models. LÄS MER
3. Key Sentence Extraction From CRISPR-Cas9 Articles Using Sentence Transformers
Master-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknikSammanfattning : The annotation of CRISPR-related articles and extraction of key content has traditionally relied on manual efforts. Manual annotation is error-prone and timeconsuming. This thesis presents an alternative approach using transfer learning and pre-trained models based on the Transformer architecture. LÄS MER
4. 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
5. 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