Tomaso A Poggio
8 papers · 2015–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
π£ Hot Topic Early Bird π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (4) π Academic Marathon (10)
π
Cross-Pollinator
(11)
π
Renaissance Researcher
(6)
πΊοΈ
Taxonomy Completionist
(20)
β
The Questioner
(2)
π
Trend Setter
Conferences
ICML (3)
NIPS (3)
ALT (1)
ICLR (1)
Top co-authors
Keywords
wasserstein distance
(1)
statistical learning
(1)
representation learning
(1)
feature learning
(1)
visual perception
(1)
signal classification
(1)
object recognition
(1)
visual cortex
(1)
multi-label learning
(1)
optimal transport
(1)
kernel approximation
(1)
reproducing kernel hilbert space
(1)
system identification
(1)
neural network model
(1)
probability measure
(1)
deep classifier
(1)
brain computation
(1)
receptive field
(1)
neural response
(1)
convolutional neural network
(1)
Papers
Position: A Theory of Deep Learning Must Include Compositional Sparsity
ICML 2025
On Generalization Bounds for Neural Networks with Low Rank Layers
ALT 2025
Formation of Representations in Neural Networks
ICLR 2025
Feature learning in deep classifiers through Intermediate Neural Collapse
ICML 2023
System Identification of Neural Systems: If We Got It Right, Would We Know?
ICML 2023
Do Deep Neural Networks Suffer from Crowding?
NIPS 2017
Learning with Group Invariant Features: A Kernel Perspective.
NIPS 2015
Learning with a Wasserstein Loss
NIPS 2015