Essays about: "Överförd inlärning"

Found 3 essays containing the words Överförd inlärning.

  1. 1. Image-Based Classification Solutions for Robust Automated Molecular Biology Labs

    University essay from KTH/Medicinteknik och hälsosystem

    Author : Arnold Teo; [2023]
    Keywords : Neural networks; Deep learning; Transfer learning; TensorFlow; Single-cell genomics; Image classification; Neurala nätverk; Djupinlärning; Överförd inlärning; TensorFlow; Enskild cellgenomik; Bildklassificering;

    Abstract : Single-cell genomics (SCG) are methods for investigating heterogeneity between biological cells, among these is Smart-seq which sequences from RNA molecules. A more recent version of this method is Smart-seq3xpress which is currently in the process of being automated by the Sandberg lab at Karolinska Institutet. READ MORE

  3. 2. Pre-training Molecular Transformers Through Reaction Prediction

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Johan Broberg; [2022]
    Keywords : Neural Networks; Transformers; Transfer Learning; Molecular Property Prediction; Reaction Prediction; Cheminformatics; Neurala nätverk; Transformers; Överförd inlärning; Prediktion av molekylers egenskaper; Reaktions prediktion; Keminformatik;

    Abstract : Molecular property prediction has the ability to improve many processes in molecular chemistry industry. One important application is the development of new drugs where molecular property prediction can decrease both the cost and time of finding new drugs. READ MORE

  4. 3. Transformer-based Model for Molecular Property Prediction with Self-Supervised Transfer Learning

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Lyu Lin; [2020]
    Keywords : Self-supervised Pre-training; Transfer Learning; Molecular Property Prediction; Transformer;

    Abstract : Molecular property prediction has a vast range of applications in the chemical industry. A powerful molecular property prediction model can promote experiments and production processes. The idea behind this degree program lies in the use of transfer learning to predict molecular properties. The project is divided into two parts. READ MORE