S
Simon Osindero
Researcher at Google
Publications - 69
Citations - 29320
Simon Osindero is an academic researcher from Google. The author has contributed to research in topics: Reinforcement learning & Artificial neural network. The author has an hindex of 26, co-authored 62 publications receiving 23560 citations. Previous affiliations of Simon Osindero include University of Toronto & University College London.
Papers
More filters
Journal ArticleDOI
A fast learning algorithm for deep belief nets
TL;DR: A fast, greedy algorithm is derived that can learn deep, directed belief networks one layer at a time, provided the top two layers form an undirected associative memory.
Posted Content
Conditional Generative Adversarial Nets
Mehdi Mirza,Simon Osindero +1 more
TL;DR: The conditional version of generative adversarial nets is introduced, which can be constructed by simply feeding the data, y, to the generator and discriminator, and it is shown that this model can generate MNIST digits conditioned on class labels.
Posted Content
Meta-Learning with Latent Embedding Optimization
Andrei Rusu,Dushyant Rao,Jakub Sygnowski,Oriol Vinyals,Razvan Pascanu,Simon Osindero,Raia Hadsell +6 more
TL;DR: In this article, a data-dependent latent generative representation of model parameters is learned and a gradient-based meta-learning is performed in a low-dimensional latent space for few-shot learning.
Proceedings Article
FeUdal Networks for Hierarchical Reinforcement Learning
Alexander Vezhnevets,Simon Osindero,Tom Schaul,Nicolas Heess,Max Jaderberg,David Silver,Koray Kavukcuoglu +6 more
TL;DR: This work introduces FeUdal Networks (FuNs), a novel architecture for hierarchical reinforcement learning inspired by the feudal reinforcement learning proposal of Dayan and Hinton, and gains power and efficacy by decoupling end-to-end learning across multiple levels -- allowing it to utilise different resolutions of time.
Journal ArticleDOI
Training Compute-Optimal Large Language Models
Jordan Hoffmann,Sebastian Borgeaud,Arthur Mensch,Elena Buchatskaya,Trevor Cai,Eliza Rutherford,Diego de Las Casas,Lisa Anne Hendricks,Johannes Welbl,Aidan Clark,Tom Hennigan,Eric Noland,Katie Millican,George van den Driessche,Bogdan Damoc,Aurelia Guy,Simon Osindero,Karen Simonyan,Erich Elsen,Jack W. Rae,Oriol Vinyals,Laurent Sifre +21 more
TL;DR: This paper trains a predicted compute-optimal model, Chinchilla, that uses the same compute budget as Gopher but with 70B parameters and 4 × more more data, and reaches a state-of-the-art average accuracy on the MMLU benchmark.