We propose information gating as a way to learn parsimonious representations that identify the minimal information required for a task.

Neural Information Processing Systems http://nips.cc/

We investigate an experiential learning paradigm for acquiring an internal model of intuitive physics. Our model is evaluated on a real-world robotic manipulation task that requires displacing objects to target locations by poking. The robot gathered over 400 hours of experience by executing more than 50K pokes on different objects. We propose a novel approach based on deep neural networks for modeling the dynamics of robot's interactions directly from images, by jointly estimating forward and inverse models of dynamics. The inverse model objective provides supervision to construct informative visual features, which the forward model can then predict and in turn regularize the feature space for the inverse model. The interplay between these two objectives creates useful, accurate models that can then be used for multi-step decision making. This formulation has the additional benefit that it is possible to learn forward models in an abstract feature space and thus alleviate the need of predicting pixels. Our experiments show that this joint modeling approach outperforms alternative methods. We also demonstrate that active data collection using the learned model further improves performance.

Neural Information Processing Systems http://nips.cc/

Humans have an extraordinary ability to perform complex operations by watching others . How do we achieve this?

We use a convolutional encoder and decoder similar to the standard DCGAN discriminator and generator architecture respectively.

Now, however, we seek an analogy to the inverse model hypothesis. "mental model" (controlled object) [36]. In both schemes, the cerebellum receives initial states upstream (instructions) and learns to mimic the forward computations which then take place in the neocortex. The properties of the forward model of the cerebellum can be set against those of backward DNI (blue); similarly, the properties of the inverse model of the cerebellum can be set against those of forward DNI (red). We split the original input into truncations as follows.