Essays about: "Generalisation"
Showing result 21 - 25 of 71 essays containing the word Generalisation.
-
21. A Study of the Loss Landscape and Metastability in Graph Convolutional Neural Networks
University essay from KTH/Matematisk statistikAbstract : Many novel graph neural network models have reported an impressive performance on benchmark dataset, but the theory behind these networks is still being developed. In this thesis, we study the trajectory of Gradient descent (GD) and Stochastic gradient descent (SGD) in the loss landscape of Graph neural networks by replicating Xing et al. READ MORE
-
22. Polyphonic Music Instrument Detection on Weakly Labelled Data using Sequence Learning Models
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : Polyphonic or multiple music instrument detection is a difficult problem compared to detecting single or solo instruments in an audio recording. As music is time series data it be can modelled using sequence learning methods within deep learning. READ MORE
-
23. The Generalist Trap - A Theoretical Exploration of Specialisation in Labour Markets
University essay from Handelshögskolan i Stockholm/Institutionen för nationalekonomiAbstract : It has previously been acknowledged that the increase in productivity resulting from time allocated to a task is a key driver of specialisation in economies. This paper presents three models exploring the topic of specialisation by assuming that the allocation of an agent's time influences production both directly and indirectly, the latter through an experience-based learning effect. READ MORE
-
24. Streaming Graph Partitioning with Graph Convolutional Networks
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : In this work, we present a novel approach to the streaming graph partitioning problem which handles unbounded streams.Graph partitioning is a process of dividing a graph into groups of nodes or edges. READ MORE
-
25. Model-Agnostic Meta-Learning for Digital Pathology
University essay from Linköpings universitet/DatorseendeAbstract : The performance of conventional deep neural networks tends to degrade when a domain shift is introduced, such as collecting data from a new site. Model-Agnostic Meta-Learning, or MAML, has achieved state-of-the-art performance in few-shot learning by finding initial parameters that adapt easily for new tasks. READ MORE
