Sökning: "Multitask Learning"

Visar resultat 6 - 9 av 9 uppsatser innehållade orden Multitask Learning.

1. 6. Multitask Convolutional Neural Network Emulators for Global Crop Models - Supervised Deep Learning in Large Hypercubes of Non-IID Data

   Master-uppsats, Lunds universitet/Matematisk statistik

   Författare :Amanda Nilsson; [2020]
   Nyckelord :Multitask Learning; Convolutional Neural Network CNN ; Branched Neural Network; Dynamic Global Vegetation Models DGVM ; Automated Feature Extraction; Feature Importance; Supervised Machine Learning; Emulator; Surrogate Model; Response Surface Model; Approximation Model; Metamodeling; Model Composition; Regularization; Robustness; Hyperparameter Optimization; Mathematics and Statistics;

   Sammanfattning : The aim of this thesis is to establish whether a neural network (NN) can be used for emulation of simulated global crop production - retrieved from the computationally demanding dynamic global vegetation model (DGVM) Lund-Potsdam-Jena General Ecosystem Simulator (LPJ-GUESS). It has been devoted to elaboration with various types of neural network architectures: Branched NNs capable of processing inputs of mixed data types; Convolutional Neural Network (CNN) architectures able to perform automated temporal feature extraction of the given weather time series; simpler fully connected (FC) structures as well as Multitask NNs. LÄS MER

3. 7. Latent Representation of Tasks for Faster Learning in Reinforcement Learning

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

   Författare :Felix Engström; [2019]
   Nyckelord :;

   Sammanfattning : Reinforcement learning (RL) is an field of machine learning (ML) which attempts to approach learning in an manner inspired by the human way of learning through rewards and penalties. As with other forms of ML, it is strongly dependent on large amounts of data, the acquisition of which can be costly and time consuming. LÄS MER

4. 8. Multitask Deep Learning models for real-time deployment in embedded systems

   Uppsats för yrkesexamina på avancerad nivå, KTH/Robotik, perception och lärande, RPL

   Författare :Miquel Martí Rabadán; [2017]
   Nyckelord :computer vision; deep learning; multitask learning; object detection; semantic segmentation; embedded systems; perception; robotics; autonomous driving;

   Sammanfattning : Multitask Learning (MTL) was conceived as an approach to improve thegeneralization ability of machine learning models. When applied to neu-ral networks, multitask models take advantage of sharing resources forreducing the total inference time, memory footprint and model size. LÄS MER

5. 9. Media och Multitasking : En studie om utbildningspodcast och träning

   Kandidat-uppsats, KTH/Skolan för datavetenskap och kommunikation (CSC)

   Författare :Rickard Björklund; Axel Weinz; [2017]
   Nyckelord :Multitasking; Education; Learning; Training; Podcast; Multitasking; Útbildning; Lärande; Träning; Podcast;

   Sammanfattning : I och med ny medieteknik samt en allt mer uppkopplad och stressad värld har det blivit vanligare med multitasking. Tidigare forskning visar att 90 procent av befolkningen multitaskar någon gång varje dag. LÄS MER