Essays about: "faltningsnätverk"
Showing result 21 - 25 of 77 essays containing the word faltningsnätverk.
-
21. Noisy recognition of perceptual mid-level features in music
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : Self-training with noisy student is a consistency-based semi-supervised self- training method that achieved state-of-the-art accuracy on ImageNet image classification upon its release. It makes use of data noise and model noise when fitting a model to both labelled data and a large amount of artificially labelled data. READ MORE
-
22. Convolutional Neural Networks: Performance on Imbalanced Data
University essay from Umeå universitet/StatistikAbstract : Imbalanced data is a major problem in machine learning classification, since predictive performance can be hindered when one class occurs more frequently than the others. For example, in medical science, imbalanced data sets are very common. READ MORE
-
23. The Effect of Beautification Filters on Image Recognition : "Are filtered social media images viable Open Source Intelligence?"
University essay from Högskolan i Halmstad/Akademin för informationsteknologiAbstract : In light of the emergence of social media, and its abundance of facial imagery, facial recognition finds itself useful from an Open Source Intelligence standpoint. Images uploaded on social media are likely to be filtered, which can destroy or modify biometric features. READ MORE
-
24. Incorporating Metadata Into the Active Learning Cycle for 2D Object Detection
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : In the past years, Deep Convolutional Neural Networks have proven to be very useful for 2D Object Detection in many applications. These types of networks require large amounts of labeled data, which can be increasingly costly for companies deploying these detectors in practice if the data quality is lacking. READ MORE
-
25. Estimating Football Position from Context
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : Tracking algorithms provide the model to recognize objects’ motion in the past. Moreover, applied to an artificial intelligence algorithm, these algorithms allow, to some degree, the capacity to forecast the future position of an object. READ MORE