Essays about: "Inbäddning"
Showing result 21 - 25 of 36 essays containing the word Inbäddning.
-
21. DistillaBSE: Task-agnostic distillation of multilingual sentence embeddings : Exploring deep self-attention distillation with switch transformers
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : The recent development of massive multilingual transformer networks has resulted in drastic improvements in model performance. These models, however, are so large they suffer from large inference latency and consume vast computing resources. Such features hinder widespread adoption of the models in industry and some academic settings. READ MORE
-
22. Finding Similarities Between Hierarchically Related Thema Subject Categories Using Embeddings
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : In this thesis, embeddings have been used to find similarities between hierarchically related Thema Subject Categories (Thema codes), which are short alphanumeric sequences commonly used to categorize books. More specifically, the graph embedding approach known as DeepWalk was applied to three different models to learn similarities between Thema codes. READ MORE
-
23. Reproduktion eller transformation : lokal mat i Ljusdalsområdet ur ett flernivåperspektiv
University essay from SLU/Dept. of Urban and Rural DevelopmentAbstract : Dagens livsmedelsförsörjningssystem orsakar stora ekologiska och so-cioekonomiska problem i samhällen över stora delar av världen och om-fattande förändringar är nödvändiga. Den dominerande livsmedelsregi-men i systemet består av ett globalt, industriellt jordbrukskomplex som involverar världsomspännande nätverk av produktion, distribution och konsumtion men också regler, normer och kulturell förståelse. READ MORE
-
24. Statistical Learning and Analysis on Homology-Based Features
University essay from KTH/Matematisk statistikAbstract : Stable rank has recently been proposed as an invariant to encode the result of persistent homology, a method used in topological data analysis. In this thesis we develop methods for statistical analysis as well as machine learning methods based on stable rank. READ MORE
-
25. A graph representation of event intervals for efficient clustering and classification
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : Sequences of event intervals occur in several application domains, while their inherent complexity hinders scalable solutions to tasks such as clustering and classification. In this thesis, we propose a novel spectral embedding representation of event interval sequences that relies on bipartite graphs. READ MORE