Shape Representation in Parallel Systems

By Geoffrey E. Hinton. 1981

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Yoshua Bengio
2. Geoffrey E. Hinton
3. Ruslan Salakhutdinov
4. Quoc V. Le
5. Sergey Levine
6. Trevor Darrell
7. J. Urgen Schmidhuber
8. Dacheng Tao

Citations in the corpus

• Dynamic Routing Between Capsules (2017, background): “[2004]), eliminates the binding problem (Hinton [1981a]) and allows a capsule to use a distributed representation (its activity vector) to encode the instantiation parameters of the entity of that type at a given location.”
• How to Represent Part-Whole Hierarchies in a Neural Network (2021, background): “That is why coarse coding, which uses a single population of broadly tuned neurons to model several different entities at the same time [Hinton, 1981a] cannot model uncertainty efficiently.”
• Theoretical Neuroscience: Computational and Mathematical Modeling of Neural Systems (2001, background): “Becker, S, & Hinton, GE (1992) A self-organizing neural network that discovers surfaces in random-dot stereograms. Nature 355:161–163. Becker, S, & Plumbley, M (1996) Unsupervised neural network learning”
• Transforming Auto-Encoders (2011, background): “Using multiple real-values is the natural way to represent pose information and it is much more efficient than using coarse coding[3], but it comes at a price: The only thing that binds the values together is the fact that they are the pose outputs of the same capsule so it is not possible for a cap”