Why and When Can Deep -- but Not Shallow -- Networks Avoid the Curse of Dimensionality: a Review

November 02, 2016 · The Cartographer · 🏛 International Journal of Automation and Computing

📚 THE CARTOGRAPHER: The Cartographer
Survey/review paper — maps the landscape rather than implementing a method.

"No code URL or promise found in abstract"
"Title-pattern auto-detect: Why and When Can Deep -- but Not Shallow -- Networks Avoid the Curse of Dimensionality: a Review"

Evidence collected by the PWNC Scanner

Authors Tomaso Poggio, Hrushikesh Mhaskar, Lorenzo Rosasco, Brando Miranda, Qianli Liao arXiv ID 1611.00740 Category cs.LG: Machine Learning Citations 623 Venue International Journal of Automation and Computing Last Checked 7 days ago
Abstract
The paper characterizes classes of functions for which deep learning can be exponentially better than shallow learning. Deep convolutional networks are a special case of these conditions, though weight sharing is not the main reason for their exponential advantage.
Community shame:
Not yet rated
📄 View on arXiv 🌐 View on ar5iv 📑 PDF 🎉 Report Code Found
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

📜 Similar Papers

In the same crypt — Machine Learning