919 citations
- Massachusetts Institute of TechnologyUS27 papers
- Harvard UniversityUS7 papers
- Institute of Cognitive and Brain SciencesUS7 papers
- Chinese Institute for Brain ResearchCN5 papers
- Tsinghua UniversityCN4 papers
- Beijing Academy of Artificial IntelligenceCN3 papers
- Beijing Normal UniversityCN3 papers
- Columbia UniversityUS3 papers
- Harvard–MIT Division of Health Sciences and TechnologyUS3 papers
- IIT@MITUS3 papers
- Italian Institute of TechnologyIT3 papers
- University of California, BerkeleyUS3 papers
4 papers · 1 filter
Why and When Can Deep -- but Not Shallow -- Networks Avoid the Curse of Dimensionality: a Review
Tomaso Poggio, Hrushikesh Mhaskar, Lorenzo Rosasco +2
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 cond…
Automated scalable segmentation of neurons from multispectral images
Uygar Sümbül, Douglas Roussien, Fei Chen +5
Reconstruction of neuroanatomy is a fundamental problem in neuroscience. Stochastic expression of colors in individual cells is a promising tool, although its use in the nervous sy…
Deep vs. shallow networks : An approximation theory perspective
Hrushikesh Mhaskar, Tomaso Poggio
The paper briefy reviews several recent results on hierarchical architectures for learning from examples, that may formally explain the conditions under which Deep Convolutional Ne…
View-tolerant face recognition and Hebbian learning imply mirror-symmetric neural tuning to head orientation
Joel Z. Leibo, Qianli Liao, Winrich Freiwald +2
The primate brain contains a hierarchy of visual areas, dubbed the ventral stream, which rapidly computes object representations that are both specific for object identity and rela…