Sökning: "weighted loss"
Visar resultat 1 - 5 av 58 uppsatser innehållade orden weighted loss.
1. Exploring patterns in risk factors for bark beetle attack during outbreaks triggered by drought stress with harvester data on attacked trees: A case study in Southeastern Sweden
Master-uppsats, Lunds universitet/Institutionen för naturgeografi och ekosystemvetenskapSammanfattning : ABSTRACT Raising temperatures and climate variability have intensified extreme weather events worldwide. These extremes can enhance and trigger possible pest outbreaks. Bark beetle attacks have become a major concern in regions with extensive spruce forest areas. Southeastern Sweden has faced repeated outbreaks resulting in widespread tree loss. LÄS MER
2. Do Stocks Outperform Treasury Bills? Evidence From a Swedish Setting
C-uppsats, Handelshögskolan i Stockholm/Institutionen för finansiell ekonomiSammanfattning : Most Swedish stocks listed since 1983 post lifetime buy-and-hold returns that are less than one-month Swedish Treasury bills. In terms of risk-adjusted returns for the same time horizon, individual Swedish stocks vastly underperform value-weighted benchmarks when measured with a Sharpe ratio. LÄS MER
3. Quantification of DNA Nanoballs Using Image Processing Techniques
Uppsats för yrkesexamina på avancerad nivå, Uppsala universitet/Avdelningen Vi3Sammanfattning : In gene editing, it is important to identify the number of edited and unedited nucleic acids in the development of new therapies and drugs. Countagen is developing a technology for accelerating genomic research and their product is called GeneAbacus. LÄS MER
4. Disambiguating Italian homographic heterophones with SoundChoice and testing ChatGPT as a data-generating tool
Master-uppsats, Uppsala universitet/Institutionen för lingvistik och filologiSammanfattning : Text-To-Speech systems are challenged by the presence of homographs, words that have more than one possible pronunciation. Rule-based approaches are often still the preferred solution to this issue in the industry. LÄS MER
5. Explainable Machine Learning in Cardiovascular Diagnostics
Kandidat-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : The major challenges in implementing machine learning models in medical applications stemfrom ethical and accountability concerns, which arise from the lack of insight and understandingof the models' inner workings and reasoning. This opaqueness has resulted in the emergenceof a new subfield of machine learning called Explainability, which aims to develop and deploymethods to gain insight into how input data is weighted and propagated through a machinelearning algorithm. LÄS MER