activity
20112026
most citedOn the difficulty of training Recurrent Neural Networks

3.8k citations · 6.5k across the 42 of their papers we have counts for

collaborators
Showing 2017Show all

6 papers · 1 filter

cs.LG201761 cited

Sobolev Training for Neural Networks

Wojciech Marian Czarnecki, Simon Osindero, Max Jaderberg +2

At the heart of deep learning we aim to use neural networks as function approximators - training them to produce outputs from inputs in emulation of a ground truth function or data…

cs.AI201778 cited

Learning model-based planning from scratch

Razvan Pascanu, Yujia Li, Oriol Vinyals +7

Conventional wisdom holds that model-based planning is a powerful approach to sequential decision-making. It is often very challenging in practice, however, because while a model c…

cs.LG2017182 cited

Distral: Robust Multitask Reinforcement Learning

Yee Whye Teh, Victor Bapst, Wojciech Marian Czarnecki +5

Most deep reinforcement learning algorithms are data inefficient in complex and rich environments, limiting their applicability to many scenarios. One direction for improving data…

cs.CV201769 cited

Visual Interaction Networks

Nicholas Watters, Andrea Tacchetti, Theophane Weber +3

From just a glance, humans can make rich predictions about the future state of a wide range of physical systems. On the other hand, modern approaches from engineering, robotics, an…

cs.CL2017503 cited

A simple neural network module for relational reasoning

Adam Santoro, David Raposo, David G. T. Barrett +4

Relational reasoning is a central component of generally intelligent behavior, but has proven difficult for neural networks to learn. In this paper we describe how to use Relation…

cs.LG201774 cited

Discovering objects and their relations from entangled scene representations

David Raposo, Adam Santoro, David Barrett +3

Our world can be succinctly and compactly described as structured scenes of objects and relations. A typical room, for example, contains salient objects such as tables, chairs and…