Sökning: "observera i TA modellen"

Visar resultat 1 - 5 av 15 uppsatser innehållade orden observera i TA modellen.

  1. 1. The effect of model calibration on noisy label detection

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Max Joel Söderberg; [2023]
    Nyckelord :Area Under the Margin; Calibration; Image classification; Label smoothing; Noisy labels; Overconfidence; Area under marginalen; Kalibrering; Bildklassificering; Etikettutjämning; Brusiga etiketter; Övertro;

    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

  3. 2. Customer Acquisition Process Digitalization: A Case Study on the Use of Machine Learning in The Corporate Insurance Industry

    Master-uppsats, KTH/Skolan för industriell teknik och management (ITM)

    Författare :Klara Larsson; Freja Ling; [2023]
    Nyckelord :Customer Relationship Management CRM ; Customer Classification; Customer Acquisition; Machine Learning; Insurance Industry; Corporate Insurance; B2B; AI-CRM; Kundrelationssystem CRM ; Kunklassificering; Nykundsbearbetning; Maskininlärning; Försäkringsbranchen; Företagsförsäkring; B2B; AI-CRM;

    Sammanfattning : This thesis explores the application of machine learning 8ml9 techniques in customer classification and their intergration into customer relationship management (CRM) systems within the corporate insurance industry. The research aims to address the gap in the use of AI-CRM for the corporate insurance industry. LÄS MER

  4. 3. Developing a supervised machine learning model for an optimised aluminium addition based on historical data analytics, for clean steelmaking

    Master-uppsats, KTH/Materialvetenskap

    Författare :Arun Kumar Thakur; [2022]
    Nyckelord :Clean steelmaking; Data analytics; De-oxidation; Machine learning; Ren ståltillverkning; Dataanalys; Deoxidation; Maskininlärning;

    Sammanfattning : De-oxidation is an important process in clean steelmaking. Al (Aluminium) is mainly used as de-oxidant and controls the final oxygen content and impact the sulphur removal in steel. Adding optimum amount of Al is critical for steel cleanliness and to reduce cost. LÄS MER

  5. 4. Beta och branscher : En studie om sambandet mellan beta och avkastning inomolika branscher

    Kandidat-uppsats, Södertörns högskola/Företagsekonomi

    Författare :Andreas Flykt; Sara Åselius; [2022]
    Nyckelord :Beta; risk; CAPM; systematisk risk; avkastning; branscher;

    Sammanfattning : I denna studie analyserar forskarna det omtalade sambandet inom finansiering mellan riskoch avkastning på den svenska aktiemarknaden. Att investera i aktier är idag närasammankopplat till begreppet risk och för investerare har sambandet mellan risk ochavkastning en mycket viktig innebörd eftersom att man ständigt söker maximal avkastning tillen minimal nivå av risk. LÄS MER

  7. 5. C/O+ charge transfer & the Olson-Demkov model

    Master-uppsats, Uppsala universitet/Teoretisk astrofysik

    Författare :Kristoffer Bengtsson; [2021]
    Nyckelord :Astronomy; Charge transfer; rate coefficient; Carbon; Oxygen; energy defect; spectral modelling; supernovae;

    Sammanfattning : Charge transfer reactions and their rates play a key role in correctly estimating element abundances in astrophysical objects such as supernovae. The reaction $C + O^+ \rightarrow C^+ + O(^1D) + \Delta E$ has been shown to be of significance when estimating oxygen abundances through model spectrum evaluations, and the relative rate of this reaction can under certain circumstances completely dictate the neutralization rate of oxygen ions. LÄS MER