no code implementations • 29 Dec 2022 • Alexey Zakharov, Qinghai Guo, Zafeirios Fountas
The task of video prediction and generation is known to be notoriously difficult, with the research in this area largely limited to short-term predictions.
no code implementations • 25 Jul 2022 • Noor Sajid, Panagiotis Tigas, Zafeirios Fountas, Qinghai Guo, Alexey Zakharov, Lancelot Da Costa
These memories are selectively attended to, using attention and gating blocks, to update agent's preferences.
1 code implementation • 14 Apr 2022 • Alexey Zakharov, Maxim Pisov, Alim Bukharaev, Alexey Petraikin, Sergey Morozov, Victor Gombolevskiy, Mikhail Belyaev
We propose a new two-step algorithm to localize the vertebral column in 3D CT images and then detect individual vertebrae and quantify fractures in 2D simultaneously.
no code implementations • 14 Jan 2022 • Zafeirios Fountas, Alexey Zakharov
Enquiries concerning the underlying mechanisms and the emergent properties of a biological brain have a long history of theoretical postulates and experimental findings.
no code implementations • ICLR 2022 • Alexey Zakharov, Qinghai Guo, Zafeirios Fountas
Discovery and learning of an underlying spatiotemporal hierarchy in sequential data is an important topic for machine learning.
no code implementations • ICML Workshop URL 2021 • Alexey Zakharov, Matthew Crosby, Zafeirios Fountas
Planning in complex environments requires reasoning over multi-step timescales.
no code implementations • ICML Workshop URL 2021 • Noor Sajid, Panagiotis Tigas, Alexey Zakharov, Zafeirios Fountas, Karl Friston
In this paper, we pursue the notion that this learnt behaviour can be a consequence of reward-free preference learning that ensures an appropriate trade-off between exploration and preference satisfaction.
no code implementations • 3 Oct 2020 • Alexey Zakharov, Matthew Crosby, Zafeirios Fountas
In model-based learning, an agent's model is commonly defined over transitions between consecutive states of an environment even though planning often requires reasoning over multi-step timescales, with intermediate states either unnecessary, or worse, accumulating prediction error.
1 code implementation • 13 Aug 2020 • Vitalis Vosylius, Andy Wang, Cemlyn Waters, Alexey Zakharov, Francis Ward, Loic Le Folgoc, John Cupitt, Antonios Makropoulos, Andreas Schuh, Daniel Rueckert, Amir Alansary
In this paper, we propose a novel approach to predict the post-menstrual age (PA) at scan, using techniques from geometric deep learning, based on the neonatal white matter cortical surface.
3 code implementations • 25 May 2020 • Maxim Pisov, Vladimir Kondratenko, Alexey Zakharov, Alexey Petraikin, Victor Gombolevskiy, Sergey Morozov, Mikhail Belyaev
Vertebral body compression fractures are reliable early signs of osteoporosis.