1 code implementation • 20 Dec 2022 • Jason Li, Nicholas Watters, Yingting, Wang, Hansem Sohn, Mehrdad Jazayeri
This not only provides a generative model of eye movements in this task but also suggests a computational theory for how humans solve the task, namely that humans use mental simulation.
1 code implementation • 25 Feb 2021 • Nicholas Watters, Joshua Tenenbaum, Mehrdad Jazayeri
In recent years, trends towards studying simulated games have gained momentum in the fields of artificial intelligence, cognitive science, psychology, and neuroscience.
no code implementations • ICLR 2020 • Sunny Duan, Loic Matthey, Andre Saraiva, Nicholas Watters, Christopher P. Burgess, Alexander Lerchner, Irina Higgins
Disentangled representations have recently been shown to improve fairness, data efficiency and generalisation in simple supervised and reinforcement learning tasks.
1 code implementation • 22 May 2019 • Nicholas Watters, Loic Matthey, Matko Bosnjak, Christopher P. Burgess, Alexander Lerchner
Data efficiency and robustness to task-irrelevant perturbations are long-standing challenges for deep reinforcement learning algorithms.
5 code implementations • 22 Jan 2019 • Christopher P. Burgess, Loic Matthey, Nicholas Watters, Rishabh Kabra, Irina Higgins, Matt Botvinick, Alexander Lerchner
The ability to decompose scenes in terms of abstract building blocks is crucial for general intelligence.
2 code implementations • 21 Jan 2019 • Nicholas Watters, Loic Matthey, Christopher P. Burgess, Alexander Lerchner
We present a simple neural rendering architecture that helps variational autoencoders (VAEs) learn disentangled representations.
no code implementations • NeurIPS 2017 • Nicholas Watters, Daniel Zoran, Theophane Weber, Peter Battaglia, Razvan Pascanu, Andrea Tacchetti
We introduce the Visual Interaction Network, a general-purpose model for learning the dynamics of a physical system from raw visual observations.
3 code implementations • 5 Jun 2017 • Nicholas Watters, Andrea Tacchetti, Theophane Weber, Razvan Pascanu, Peter Battaglia, Daniel Zoran
We found that from just six input video frames the Visual Interaction Network can generate accurate future trajectories of hundreds of time steps on a wide range of physical systems.