Sökning: "no time for us"
Visar resultat 1 - 5 av 464 uppsatser innehållade orden no time for us.
1. Self-Supervised Learning for Tabular Data: Analysing VIME and introducing Mix Encoder
Kandidat-uppsats, Lunds universitet/Fysiska institutionenSammanfattning : We introduce Mix Encoder, a novel self-supervised learning framework for deep tabular data models based on Mixup [1]. Mix Encoder uses linear interpolations of samples with associated pretext tasks to form useful pre-trained representations. LÄS MER
2. The Public, The Police, and The Puzzle of Information
Magister-uppsats, Lunds universitet/Avdelningen för Riskhantering och SamhällssäkerhetSammanfattning : When humans are involved, things can go wrong. This is a statement as factually true and yet dramatically undefined and dangerously ambiguous as any. No matter the industry or domain, where humans interact with other humans, perfect predictability is impossible and a focus on negative outcomes can seem natural. LÄS MER
3. Offentlig konst inom vård- och omsorgsboenden - En undersökning om äldres delaktighet vid val av konst på vård- och omsorgsboenden
Kandidat-uppsats, Göteborgs universitet/Institutionen för kulturvetenskaperSammanfattning : Since 2013, Gothenburg's Art unit has been given responsibility for all art in the city's nursing homes, they are a part of the public administration. Gothenburg Art describes in an article published in 2014 that, according to their mission, art should simulate and evoke discussion among the elderly. LÄS MER
4. Evaluating Brain-Inspired Machine Learning Models for Time Series Forecasting: A Comparative Study on Dynamical Memory in Reservoir Computing and Neural Networks
Kandidat-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Brain-inspired computing is a promising research field, with potential to encouragebreakthroughs within machine learning and enable us to solve complex problems in a moreefficient way. This study aims to compare the performance of brain-like machine learningalgorithms for time series forecasting. LÄS MER
5. Exploration of using Twitter data to predict Swedish political opinion polls with neural networks
Master-uppsats, Lunds universitet/Matematisk statistikSammanfattning : This thesis aims to explore the possibility of using deep learning techniques to mine opinions on Twitter, with the objective to predict the political opinion distribution in Sweden. Different methods of gathering and annotating training data are evaluated to achieve accurate and reliable predictions. LÄS MER