no code implementations • 4 Mar 2024 • Maneesha Perera, Julian De Hoog, Kasun Bandara, Damith Senanayake, Saman Halgamuge
In this work, we propose two deep-learning-based regional forecasting methods that can effectively leverage both types of time series (aggregated and individual) with weather data in a region.
no code implementations • 6 Jan 2024 • Haihang Wu, Wei Wang, Tamasha Malepathirana, Damith Senanayake, Denny Oetomo, Saman Halgamuge
Neural growth is the process of growing a small neural network to a large network and has been utilized to accelerate the training of deep neural networks.
1 code implementation • 18 Dec 2023 • Nisal Ranasinghe, Damith Senanayake, Sachith Seneviratne, Malin Premaratne, Saman Halgamuge
In this work, we propose GINN-LP, an interpretable neural network to discover the form and coefficients of the underlying equation of a dataset, when the equation is assumed to take the form of a multivariate Laurent Polynomial.
1 code implementation • 18 Aug 2023 • Tamasha Malepathirana, Damith Senanayake, Saman Halgamuge
However, due to the lack of old data, NECIL methods struggle to discriminate between old and new classes causing their feature representations to overlap.
Incremental Learning Non-exemplar-based Class Incremental Learning +1
1 code implementation • ICCV 2023 • Tamasha Malepathirana, Damith Senanayake, Saman Halgamuge
However, due to the lack of old data, NECIL methods struggle to discriminate between old and new classes causing their feature representations to overlap.
Incremental Learning Non-exemplar-based Class Incremental Learning +1
1 code implementation • 3 Aug 2022 • Sachith Seneviratne, Damith Senanayake, Sanka Rasnayaka, Rajith Vidanaarachchi, Jason Thompson
However, a detailed analysis capturing the capabilities of such models, specifically with a focus on the built environment, has not been performed to date.
1 code implementation • 9 Dec 2019 • Damith Senanayake, Wei Wang, Shalin H. Naik, Saman Halgamuge
In addition, SONG is capable of handling new data increments, no matter whether they are similar or heterogeneous to the already observed data distribution.