Sökning: "classification robustness"
Visar resultat 1 - 5 av 55 uppsatser innehållade orden classification robustness.
1. Robustness Against Non-Normality : Evaluating LDA and QDA in Simulated Settings Using Multivariate Non-Normal Distributions
Kandidat-uppsats, Uppsala universitet/Statistiska institutionenSammanfattning : Evaluating classifiers in controlled settings is essential for empirical applications, as extensive knowledge on model-behaviour is needed for accurate predictions. This thesis investigates robustness against non-normality of two prominent classifiers, LDA and QDA. LÄS MER
2. Testing and Integration of Machine Learning Components for Image Classification : Testning och integration av machine learning komponenter förbildklassificering
Master-uppsats, Linköpings universitet/Institutionen för datavetenskapSammanfattning : As ML (Machine Learning) and deep neural networks get more used in many systems,the need to understand and test such systems becomes more actual. When designing a newsystem that contains ML models, the safety of this system becomes inevitably important. LÄS MER
3. Anomaly Detection with Machine Learning using CLIP in a Video Surveillance Context
Master-uppsats, Linköpings universitet/DatorseendeSammanfattning : This thesis explores the application of Contrastive Language-Image Pre-Training (CLIP), a vision-language model, in an automated video surveillance system for anomaly detection. The ability of CLIP to perform zero-shot learning, coupled with its robustness against minor image alterations due to its lack of reliance on pixel-level image analysis, makes it a suitable candidate for this application. LÄS MER
4. The effect of model calibration on noisy label detection
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : The advances in deep neural networks in recent years have opened up the possibility of using image classification as a valuable tool in various areas, such as medical diagnosis from x-ray images. However, training deep neural networks requires large amounts of annotated data which has to be labelled manually, by a person. LÄS MER
5. Decoding communication of non-human species - Unsupervised machine learning to infer syntactical and temporal patterns in fruit-bats vocalizations.
Master-uppsats, Stockholms universitet/Institutionen för data- och systemvetenskapSammanfattning : Decoding non-human species communication offers a unique chance to explore alternative intelligence forms using machine learning. This master thesis focuses on discreteness and grammar, two of five linguistic areas machine learning can support, and tackles inferring syntax and temporal structures from bioacoustics data annotated with animal behavior. LÄS MER