no code implementations • 31 Jul 2023 • Arinbjörn Kolbeinsson, Luca Foschini
Data scarcity is a common obstacle in medical research due to the high costs associated with data collection and the complexity of gaining access to and utilizing data.
1 code implementation • 14 Nov 2020 • Daniel Lengyel, Janith Petangoda, Isak Falk, Kate Highnam, Michalis Lazarou, Arinbjörn Kolbeinsson, Marc Peter Deisenroth, Nicholas R. Jennings
We propose an efficient algorithm to visualise symmetries in neural networks.
no code implementations • 29 Aug 2020 • Kyriaki-Margarita Bintsi, Vasileios Baltatzis, Arinbjörn Kolbeinsson, Alexander Hammers, Daniel Rueckert
Many studies have been proposed for the prediction of chronological age from brain MRI using machine learning and specifically deep learning techniques.
no code implementations • 25 Nov 2019 • Pierre H. Richemond, Arinbjörn Kolbeinsson, Yike Guo
Deep reinforcement learning requires a heavy price in terms of sample efficiency and overparameterization in the neural networks used for function approximation.
1 code implementation • 24 Sep 2019 • Akhil Gupta, Naman Shukla, Lavanya Marla, Arinbjörn Kolbeinsson, Kartik Yellepeddi
We focus on incorporating monotonic trends, and propose a novel gradient-based point-wise loss function for enforcing partial monotonicity with deep neural networks.
no code implementations • 21 May 2019 • Naman Shukla, Arinbjörn Kolbeinsson, Lavanya Marla, Kartik Yellepeddi
Multiple machine learning and prediction models are often used for the same prediction or recommendation task.
no code implementations • 27 Feb 2019 • Arinbjörn Kolbeinsson, Jean Kossaifi, Yannis Panagakis, Adrian Bulat, Anima Anandkumar, Ioanna Tzoulaki, Paul Matthews
CNNs achieve remarkable performance by leveraging deep, over-parametrized architectures, trained on large datasets.
no code implementations • 6 Feb 2019 • Naman Shukla, Arinbjörn Kolbeinsson, Ken Otwell, Lavanya Marla, Kartik Yellepeddi
We also measure the real-world business impact of these approaches by deploying them in an A/B test on an airline's internet booking website.