Demonstration venue · read-only. Every page can be browsed; the buttons that would change it are switched off. Create an account to run TaxoReview on your own data. A simulation from public publication records: the people listed were not invited and did not agree to review.
? Tutorial for this page
Demo Data from EDBT 2026 / reviewers in the wild / expert

Yizhang Lou

dblp:304/8803 · DBLP profile ↗
← Back
1ranked-venue papers
1as first author
1since 2021 · last 2022
—ORCID · none

Domains — the database's venue-derived domains; a paper can count in several

Artificial intelligence and machine learning · 1 · 1 first-author · 1 since 2021

Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.

Artificial intelligence
1 paper
Learning theory · 67% Representation and self-supervised learning · 33%

Topics — the 3 heaviest of 3, each with the papers that count most for it

TopicWeightPapersLastEvidence papers
Machine learning › Learning theory › neural network theory › feature learning theory
feature learning dynamics		 0.612022
Feature Learning and Signal Propagation in Deep Neural Networks · ICML 2022
Machine learning › Representation and self-supervised learning › representation matching › feature alignment
layer alignment		 0.612022
Feature Learning and Signal Propagation in Deep Neural Networks · ICML 2022
Machine learning › Learning theory
neural network theory		 0.612022
Feature Learning and Signal Propagation in Deep Neural Networks · ICML 2022

Methods — techniques the papers use, named apart from their topics

tangent feature analysis · 0.6
YearPublicationVenuePosition
2022 Feature Learning and Signal Propagation in Deep Neural Networks
abstract
Recent work by Baratin et al. (2021) sheds light on an intriguing pattern that occurs during the training of deep neural networks: some layers align much more with data compared to other layers (where the alignment is defined as the normalize euclidean product of the tangent features matrix and the data labels matrix). The curve of the alignment as a function of layer index (generally) exhibits a ascent-descent pattern where the maximum is reached for some hidden layer. In this work, we provide the first explanation for this phenomenon. We introduce the Equilibrium Hypothesis which connects this alignment pattern to signal propagation in deep neural networks. Our experiments demonstrate an excellent match with the theoretical predictions.
Yizhang Lou, Chris Mingard, Soufiane Hayou
 ICML1