Geometrical Singularities in the Neuromanifold of Multilayer Perceptrons

By Shun-ichi Amari, Hyeyoung Park, Tomoko Ozeki. 2001

36 citations recorded by the source corpus.

Subfields: Analytical Chemistry, Artificial Intelligence, Model Architectures, Signal Processing

How researchers see this paper

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

In Analytical Chemistry

1. Yoshua Bengio

In Artificial Intelligence

1. Yoshua Bengio
2. Razvan Pascanu
3. Kyunghyun Cho
4. Sergey Levine
5. Mohit Bansal
6. Quoc V. Le
7. Ruslan Salakhutdinov
8. Jianfeng Gao

In Model Architectures

1. Razvan Pascanu
2. Yoshua Bengio
3. Kyunghyun Cho
4. J. Urgen Schmidhuber
5. Quoc V. Le
6. Aaron C. Courville
7. Li Deng
8. Oriol Vinyals

In Signal Processing

1. Yoshua Bengio
2. Razvan Pascanu
3. Mirco Ravanelli
4. Justin Bayer
5. Li Deng
6. Kyunghyun Cho
7. Ilya Sutskever
8. Christian Osendorfer

Citations in the corpus

• Revisiting Natural Gradient for Deep Networks (2013, background): “rmulation of the training objective. In Park et al. (2000) such plateaux are seen as singularities of the functional manifold, providing a nice framework to study them (as is done for example in ichi Amari et al. (2001), Fukumizu and ichi Amari (2000)). An argument that can be made in favor of Uat p”
• Dynamics of Learning Near Singularities in Layered Networks (2008, unknown): “statistical community (e.g., Hartigan, 1985; Dacunha-Castelle & Gassiat, 1997; Amari, Park, & Ozeki, 2002 ).”