Difference between revisions of "Generative Query Network (GQN)"
| Line 3: | Line 3: | ||
* [[Inside Out - Curious Optimistic Reasoning]] | * [[Inside Out - Curious Optimistic Reasoning]] | ||
* [[Reinforcement (RL)]] | * [[Reinforcement (RL)]] | ||
| − | + | ||
| + | A framework within which machines learn to perceive their surroundings by training only on data obtained by themselves as they move around scenes. Much like infants and animals, the GQN learns by trying to make sense of its observations of the world around it. In doing so, the GQN learns about plausible scenes and their geometrical properties, without any human labelling of the contents of scenes. The GQN model is composed of two parts: a representation network and a generation network. The representation network takes the agent's observations as its input and produces a representation (a vector) which describes the underlying scene. The generation network then predicts (‘imagines’) the scene from a previously unobserved viewpoint. [http://deepmind.com/documents/211/Neural_Scene_Representation_and_Rendering_preprint.pdf Neural Scene Representation and Rendering | Science] | ||
| + | |||
| + | https://i0.wp.com/big4all.org/wp-content/uploads/2018/06/example_gqn.png? | ||
<youtube>N0Ld2iTMaMs</youtube> | <youtube>N0Ld2iTMaMs</youtube> | ||
| + | <youtube>RBJFngN33Qo</youtube> | ||
Revision as of 18:50, 28 June 2018
A framework within which machines learn to perceive their surroundings by training only on data obtained by themselves as they move around scenes. Much like infants and animals, the GQN learns by trying to make sense of its observations of the world around it. In doing so, the GQN learns about plausible scenes and their geometrical properties, without any human labelling of the contents of scenes. The GQN model is composed of two parts: a representation network and a generation network. The representation network takes the agent's observations as its input and produces a representation (a vector) which describes the underlying scene. The generation network then predicts (‘imagines’) the scene from a previously unobserved viewpoint. Neural Scene Representation and Rendering | Science
?
