Sökning: "parametrar för klassificering"
Visar resultat 1 - 5 av 57 uppsatser innehållade orden parametrar för klassificering.
1. The impact of pruning Convolutional Neural Networks when classifying skin cancer
Kandidat-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Over the past few years, there have been multiple reports showcasing how Convolutional Neural Networks (CNNs) can be used to classify if skin lesions are cancerous or non-cancerous. However, a limitation of CNNs is the large number of parameters resulting in high computation times. LÄS MER
2. An Evaluation of Classical and Quantum Kernels for Machine Learning Classifiers
Kandidat-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Quantum computing is an emerging field with potential applications in machine learning. This research project aimed to compare the performance of a quantum kernel to that of a classical kernel in machine learning binary classification tasks. LÄS MER
3. Sömnregistrering med hjälp av ActiGraph GT9X Link och Polar Vantage V2 - en jämförande studie
Uppsats för yrkesexamina på grundnivå, Uppsala universitet/Pediatrisk inflammations- och metabolismforskning samt barnhälsaSammanfattning : Background: In recent years the interest in self-care has expanded, with sleep playing a big part. Concurrently, the development of self-monitoring wristwatches has enabled individuals to track their sleep. Commonly these are called sleep trackers. LÄS MER
4. Comparison of CNN and LSTM for classifying short musical samples
Kandidat-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Applying machine learning to music and audio data is becoming increasingly common. One such area of research is instrument classification, which is the task of identifying the instrument played in a given audio file. In this study, we compared two machine learning model types, LSTM and CNN, on the task of classifying ten different instruments. LÄS MER
5. Computer-Aided Characterization of Lung - Segmentation and Vessel Tree Analysis Algorithms for Clinical Research Applications
Master-uppsats, KTH/FysikSammanfattning : The initial stage of a lung examination involves the segmentation of a CT image, a process that has been put under a lot of pressure with the high demand for chest scans and accurate segmentations. Current automatic segmentation algorithms are either non-robust for different datasets, not easily accessible, or time-consuming. LÄS MER