arXiv
Open Access
2017
The energy landscape of a simple neural network
Anthony Collins Gamst
Alden Walker
Abstrak
We explore the energy landscape of a simple neural network. In particular, we expand upon previous work demonstrating that the empirical complexity of fitted neural networks is vastly less than a naive parameter count would suggest and that this implicit regularization is actually beneficial for generalization from fitted models.
Penulis (2)
A
Anthony Collins Gamst
A
Alden Walker
Akses Cepat
Informasi Jurnal
- Tahun Terbit
- 2017
- Bahasa
- en
- Sumber Database
- arXiv
- Akses
- Open Access ✓