Výsledky vyhledávání - "Wijesinghe, Rukshan"

Report

Neural Mixture Models with Expectation-Maximization for End-to-end Deep Clustering

Autor: Tissera, Dumindu, Vithanage, Kasun, Wijesinghe, Rukshan, Xavier, Alex, Jayasena, Sanath, Fernando, Subha, Rodrigo, Ranga

Any clustering algorithm must synchronously learn to model the clusters and allocate data to those clusters in the absence of labels. Mixture model-based methods model clusters with pre-defined statistical distributions and allocate data to those clu

Externí odkaz: http://arxiv.org/abs/2107.02453

Zobrazit plný text záznamu

Report

Transferring Domain Knowledge with an Adviser in Continuous Tasks

Autor: Wijesinghe, Rukshan, Vithanage, Kasun, Tissera, Dumindu, Xavier, Alex, Fernando, Subha, Samarawickrama, Jayathu

Recent advances in Reinforcement Learning (RL) have surpassed human-level performance in many simulated environments. However, existing reinforcement learning techniques are incapable of explicitly incorporating already known domain-specific knowledg

Externí odkaz: http://arxiv.org/abs/2102.08029

Zobrazit plný text záznamu

Report

Feature-Dependent Cross-Connections in Multi-Path Neural Networks

Autor: Tissera, Dumindu, Vithanage, Kasun, Wijesinghe, Rukshan, Kahatapitiya, Kumara, Fernando, Subha, Rodrigo, Ranga

Learning a particular task from a dataset, samples in which originate from diverse contexts, is challenging, and usually addressed by deepening or widening standard neural networks. As opposed to conventional network widening, multi-path architecture

Externí odkaz: http://arxiv.org/abs/2006.13904

Zobrazit plný text záznamu

Report

Context-Aware Multipath Networks

Autor: Tissera, Dumindu, Kahatapitiya, Kumara, Wijesinghe, Rukshan, Fernando, Subha, Rodrigo, Ranga

Making a single network effectively address diverse contexts---learning the variations within a dataset or multiple datasets---is an intriguing step towards achieving generalized intelligence. Existing approaches of deepening, widening, and assemblin

Externí odkaz: http://arxiv.org/abs/1907.11519

Zobrazit plný text záznamu