Sökning: "Self-training"
Visar resultat 1 - 5 av 13 uppsatser innehållade ordet Self-training.
1. Patienters upplevelse av aktiv träning med inspiration från VASA-konceptet för att förebygga eller minska hemiparetisk skuldersmärta efter stroke.
Magister-uppsats, Uppsala universitet/FysioterapiSammanfattning : Bakgrund Hemiparetisk skuldersmärta (HPS) efter stroke är vanligt med en prevalens mellan 22-47%. I nuläget finns ingen optimal behandling för HPS och de nationella riktlinjerna rekommenderar stödjande hjälpmedel som behandling trots att patienter beskrivit dessa som negativa. Därför föreslås en mer aktiv behandling mot HPS. LÄS MER
2. Semi-Supervised Domain Adaptation for Semantic Segmentation with Consistency Regularization : A learning framework under scarce dense labels
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Learning from unlabeled data is a topic of critical significance in machine learning, as the large datasets required to train ever-growing models are costly and impractical to annotate. Semi-Supervised Learning (SSL) methods aim to learn from a few labels and a large unlabeled dataset. LÄS MER
3. Using Semi-Supervised Learning for Email Classification
Master-uppsats, KTH/Matematik (Avd.)Sammanfattning : In this thesis, we investigate the use of self-training, a semi-supervised learning method, to improve binary classification of text documents. This means making use of unlabeled samples, since labeled samples can be expensive to generate. More specifically, we want to classify emails that are retrieved by Skandinaviska Enskilda Banken (SEB). LÄS MER
4. Improving a Few-shot Named Entity Recognition Model Using Data Augmentation
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : To label words of interest into a predefined set of named entities have traditionally required a large amount of labeled in-domain data. Recently, the availability of pre-trained transformer-based language models have enabled multiple natural language processing problems to utilize transfer learning techniques to construct machine learning models with less task-specific labeled data. LÄS MER
5. Deep Ensembles for Self-Training in NLP
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : With the development of deep learning methods the requirement of having access to large amounts of data has increased. In this study, we have looked at methods for leveraging unlabeled data while only having access to small amounts of labeled data, which is common in real-world scenarios. LÄS MER