Classification of Systems-II
Generalization, Discrimination, and Extinction
Aggregates Classification
Classification of Systems-I
Survival Tree
Parameters Affecting Nonlinear Elimination: Zero-Order Input, First-Order Absorption and Two-Compartment Model
You might also read
Articles linked to this work by shared authors, journal, and citation graph.
Updated: Jul 29, 2025

Deep Neural Networks for Image-Based Dietary Assessment
Published on: March 13, 2021
Mengjia Xu1,2, Akshay Rangamani1, Qianli Liao1
1Center for Brains, Minds and Machines, Massachusetts Institute of Technology, Cambridge, MA, USA.
This study explores training deep neural networks with square loss, revealing how weight decay and gradient descent influence solutions. Findings include improved bounds for convolutional layers and a bias toward low-rank matrices, enhancing generalization and predicting neural collapse.
Area of Science:
Background:
Purpose of the Study:
Main Methods:
Main Results:
Conclusions: