Related Experiment Video
Updated: Dec 27, 2025

Deep Neural Networks for Image-Based Dietary Assessment
Published on: March 13, 2021
Complexity control by gradient descent in deep networks
Tomaso Poggio1, Qianli Liao2, Andrzej Banburski2
1Center for Brains, Minds, and Machines, MIT, Cambridge, Massachusetts, USA. tp@ai.mit.edu.
Abstract:
Overparametrized deep networks predict well, despite the lack of an explicit complexity control during training, such as an explicit regularization term. For exponential-type loss functions, we solve this puzzle by showing an effective regularization effect of gradient descent in terms of the normalized weights that are relevant for classification.
Related Concept Videos
Gradient and Del Operator
Hierarchy of Motor Control
Control Systems
At the heart...
Multi-input and Multi-variable systems
In the absence of...
Neural Regulation
Neural Control of Respiration
Respiratory Centers in the Brainstem
Two primary areas comprise the respiratory center: the medullary respiratory center in the medulla oblongata and the pontine respiratory group in the pons. The...
