Generalization, Discrimination, and Extinction
Associative Learning
Survival Tree
Parameters Affecting Nonlinear Elimination: Zero-Order Input, First-Order Absorption and Two-Compartment Model
Introduction to Learning
Normal and Tangetial Components: Problem Solving
You might also read
Articles linked to this work by shared authors, journal, and citation graph.
Updated: Sep 11, 2025

Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques
Published on: June 30, 2020
1The Institute of Statistical Mathematics, Tokyo 190-8562, Japan bao.han@ism.ac.jp.
Feature normalization is crucial for preventing collapse in noncontrastive learning. This study shows cosine loss, unlike L2 loss, induces stable dynamics, ensuring robust representation learning without negative examples.
Area of Science:
Background:
Purpose of the Study:
Main Methods:
Main Results:
Conclusions: