no code implementations • 22 Feb 2024 • Dmitry Kangin, Plamen Angelov
Through quantitative analysis, as well as qualitative interpretations of decision making, we demonstrate that the suggested method can improve upon existing baselines, as well as showcase the limitations of such approach yet to be solved.
no code implementations • 19 Nov 2023 • Plamen Angelov, Dmitry Kangin, Ziyang Zhang
The proposed framework named IDEAL (Interpretable-by-design DEep learning ALgorithms) recasts the standard supervised classification problem into a function of similarity to a set of prototypes derived from the training data, while taking advantage of existing latent spaces of large neural networks forming so-called Foundation Models (FM).
1 code implementation • ICLR 2022 • Andrew Corbett, Dmitry Kangin
Continuous-depth neural networks, such as Neural ODEs, have refashioned the understanding of residual neural networks in terms of non-linear vector-valued optimal control problems.
1 code implementation • 2 Apr 2021 • Suman Ravuri, Karel Lenc, Matthew Willson, Dmitry Kangin, Remi Lam, Piotr Mirowski, Megan Fitzsimons, Maria Athanassiadou, Sheleem Kashem, Sam Madge, Rachel Prudden, Amol Mandhane, Aidan Clark, Andrew Brock, Karen Simonyan, Raia Hadsell, Niall Robinson, Ellen Clancy, Alberto Arribas, Shakir Mohamed
To address these challenges, we present a Deep Generative Model for the probabilistic nowcasting of precipitation from radar.
no code implementations • 11 May 2020 • Rachel Prudden, Samantha Adams, Dmitry Kangin, Niall Robinson, Suman Ravuri, Shakir Mohamed, Alberto Arribas
A 'nowcast' is a type of weather forecast which makes predictions in the very short term, typically less than two hours - a period in which traditional numerical weather prediction can be limited.
2 code implementations • ICLR 2019 • Dmitry Kangin, Nicolas Pugeault
Building upon the recent success of deep reinforcement learning methods, we investigate the possibility of on-policy reinforcement learning improvement by reusing the data from several consecutive policies.
no code implementations • 15 Mar 2018 • Sen He, Dmitry Kangin, Yang Mi, Nicolas Pugeault
In this paper, we apply the attention mechanism to autonomous driving for steering angle prediction.
no code implementations • ICLR 2018 • Dmitry Kangin, Nicolas Pugeault
In this article we propose a model-free control method, which uses a combination of reinforcement and supervised learning for autonomous control and paves the way towards policy based control in real world environments.