Sökning: "UMAP"

Visar resultat 1 - 5 av 9 uppsatser innehållade ordet UMAP.

1. 1. Decoding communication of non-human species - Unsupervised machine learning to infer syntactical and temporal patterns in fruit-bats vocalizations.

   Master-uppsats, Stockholms universitet/Institutionen för data- och systemvetenskap

   Författare :Luigi Assom; [2023]
   Nyckelord :animal decision making; unsupervised machine learning; UMAP; autoencoders; classifiers; bioacoustics; combinatory syntax; animal communication;

   Sammanfattning : Decoding non-human species communication offers a unique chance to explore alternative intelligence forms using machine learning. This master thesis focuses on discreteness and grammar, two of five linguistic areas machine learning can support, and tackles inferring syntax and temporal structures from bioacoustics data annotated with animal behavior. LÄS MER

3. 2. Predictive maintenance using NLP and clustering support messages

   Magister-uppsats, Luleå tekniska universitet/Institutionen för system- och rymdteknik

   Författare :Ugur Yilmaz; [2022]
   Nyckelord :Predictive maintenance; support messages; NLP; unsupervised clustering; intent recognition; LDA; UMAP; HDBSCAN; BERT; Swedish BERT KB-BERT ; Billogram;

   Sammanfattning : Communication with customers is a major part of customer experience as well as a great source of data mining. More businesses are engaging with consumers via text messages. Before 2020, 39% of businesses already use some form of text messaging to communicate with their consumers. Many more were expected to adopt the technology after 2020[1]. LÄS MER

4. 3. Clustering SQL-queries using unsupervised machine learning

   Uppsats för yrkesexamina på avancerad nivå, Luleå tekniska universitet/Institutionen för system- och rymdteknik

   Författare :Thomas Schmidt; [2022]
   Nyckelord :unsupervised machine learning; machine learning; SQL; AI; clustering;

   Sammanfattning : Decerno has created a business system that utilizes Microsoft's Entity Framework (EF) which is an object-database mapper. It can automatically generate SQL queries from code written in C#. Some of these queries has started to display significant increase in query response time which require further examination. LÄS MER

5. 4. Demography of Birch Populations across Scandinavia

   Master-uppsats, Uppsala universitet/Växtekologi och evolution; Uppsala universitet/Institutionen för biologisk grundutbildning

   Författare :Janek Sendrowski; [2022]
   Nyckelord :birch; betula; pubescens; pendula; betula pubescens; betula pendula; silver birch; downy birch; demography; population structure; distribution of fitness effects; DFE; dadi; UMAP; PCA; ADMIXTURE; polyDFE; ice age; glaciation; tree; boreal forest; climate change; adaption; tetraploid; diploid-tetraploid introgression; Scandinavia; genetic cluster; pipeline; snakemake; bioinformatics; reproducible; population genetics; postglacial population expansion; demographic history; FEEMS; site-frequency spectrum; SFS; last glacial maximum; LGM; workflow; python; population expansion; population growth; EST-SFS; 0-fold degenerate; 4-fold degenerate; maximum likelihood estimation; MLE; variant call format; VCF; single-nucleotide polymorphism; SNP;

   Sammanfattning : Boreal forests are particularly vulnerable to climate change, experiencing a much more drastic increase in temperatures and having a limited amount of more northern refugia. The trees making up these vast and important ecosystems already had to adapt previously to environmental pressures brought about by the repeated glaciations during past ice ages. LÄS MER

7. 5. Uncovering Correlations Between Two UMAP Hyperparameters and the Input Dataset

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Federico Jimenez Villalonga; [2021]
   Nyckelord :;

   Sammanfattning : Learning small high-dimensional image datasets can be challenging: while deep learning models struggle, because of the limited data, simpler machine learning models can be slow, due to the high number of features. UMAP is a dimensionality reduction method that creates low dimensional representations of the datasets, which can be used as input to simple models, reducing the computational time. LÄS MER