Advanced search
Showing result 1 - 5 of 8 essays matching the above criteria.
-
1. Investigation of Information-Theoretic Bounds on Generalization Error
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : Generalization error describes how well a supervised machine learning algorithm predicts the labels of input data that it has not been trained with. This project aims to explore two different methods for bounding generalization error, f-CMI and ISMI, which explicitly use mutual information. READ MORE
-
2. How do we know when a player is fully recovered? : A systematic review about return to play
University essay from Högskolan i Skövde/Institutionen för biovetenskapAbstract : Athletes participating in ice hockey are at a high risk of experiencing a concussion which can lead to impairments in cognitive functions. Deciding when a player can be returned to playing ice hockey is part of the concussion management called return to play (RTP). This can bebased on subjective or objective measures. READ MORE
-
3. Opportunities for increased nutrient recovery at centralised wastewater treatment plants through urine separation
University essay from Uppsala universitet/Institutionen för geovetenskaperAbstract : Municipal wastewater contains a significant amount of nutrients such as phosphorus (P) and nitrogen (N). Therefore have the interest of recovering these nutrients at wastewater treatment plants (WWTP) increased. Nutrient recovery would generate revenue for the WWTP, as it is possible to sell the products as fertiliser. READ MORE
-
4. UCII® och Cartrophen vet. som behandlingsalternativ vid osteoartrit hos hund
University essay from SLU/Dept. of Biomedical Sciences and Veterinary Public HealthAbstract : Osteoartrit (OA) är en utbredd sjukdom hos hund som affekterar drygt en femtedel av hela populationen. Sjukdomen är kronisk och självdrivande, där fokus inom dagens veterinärmedicin ligger på smärtlindring och där det är möjligt kirurgiskt åtgärda eventuellt primär bakomliggande leddefekt. READ MORE
-
5. Rating corrumption within insurance companies using Bayesian network classifiers
University essay from Umeå universitet/StatistikAbstract : Bayesian Network (BN) classifiers are a type of probabilistic models. The learning process consists of two steps, structure learning and parameter learning. Four BN classifiers will be learned. These are two different Naive Bayes classifiers (NB), one Tree Augmented Naive Bayes classifier (TAN) and one Forest Naive Bayes classifier (FAN). READ MORE