Developing Population Codes by Minimizing Description Length
By Richard S. Zemel, Geoffrey E. Hinton. 1993
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Yoshua Bengio
- Ruslan Salakhutdinov
- Xiaogang Wang
- Trevor Darrell
- Sergey Levine
- Dacheng Tao
- Quoc V. Le
- J. Urgen Schmidhuber
Citations in the corpus
- Deep learning in neural networks: An overview (2014, background): “Many UL methods are designed to maximize information-theoretic objectives (e.g., Linsker, 1988; Barlow et al., 1989; MacKay and Miller, 1990; Plumbley, 1991; Schmidhuber, 1992b,c; Schraudolph and Sejnowski, 1993; Redlich, 1993; Zemel, 1993; Zemel and Hinton, 1994; Field, 1994; Hinton et al., 1995; D”
- Principal Manifolds and Probabilistic Subspaces for Visual Recognition (2002, background): “3 corresponding to nonlinear projection, approximate reconstruction and, typically, no prior knowledge regarding the joint distribution of the components, respectively (however, see Zemel and Hinton [45] for an example of devising suitable priors in such cases).”
- The Indian Buffet Process: An Introduction and Review (2011, methodology): “Latent feature values can be continuous, as in factor analysis (Roweis and Ghahramani, 1999) and probabilistic principal component analysis (PCA; Tipping and Bishop, 1999), or discrete, as in cooperative vector quantization (CVQ; Zemel and Hinton, 1994; Ghahramani, 1995).”
- Infinite latent feature models and the Indian buffet process (2005, background): “Latent feature values can be continuous, as in principal component analysis (PCA) [2], or discrete, as in cooperative vector quantization (CVQ) [3, 4].”
- Feature Extraction Through LOCOCODE (1999, background): “…it does not depend on explicit terms enforcing independence (e.g., Schmidhuber, 1992), zero mutual information among code components (e.g., Linsker, 1988; Deco & Parra, 1994), or sparseness (e.g., Field, 1994; Zemel & Hinton, 1994; Olshausen & Field, 1996; Zemel, 1993; Hinton & Ghahramani, 1997).”
- Autoencoders, Minimum Description Length and Helmholtz Free Energy (1993, methodology): “In related work (Zemel and Hinton 1994) we apply the same approach to learning population codes.”