42 citations · 181 across the 14 of their papers we have counts for
7 papers · 1 filter
Distribution of Classification Margins: Are All Data Equal?
Andrzej Banburski, Fernanda De La Torre, Nishka Pant +2
Recent theoretical results show that gradient descent on deep neural networks under exponential loss functions locally maximizes classification margin, which is equivalent to minim…
Biologically Inspired Mechanisms for Adversarial Robustness
Manish V. Reddy, Andrzej Banburski, Nishka Pant +1
A convolutional neural network strongly robust to adversarial perturbations at reasonable computational and performance cost has not yet been demonstrated. The primate visual ventr…
Hierarchically Compositional Tasks and Deep Convolutional Networks
Arturo Deza, Qianli Liao, Andrzej Banburski +1
The main success stories of deep learning, starting with ImageNet, depend on deep convolutional networks, which on certain tasks perform significantly better than traditional shall…
Theoretical Issues in Deep Networks: Approximation, Optimization and Generalization
Tomaso Poggio, Andrzej Banburski, Qianli Liao
While deep learning is successful in a number of applications, it is not yet well understood theoretically. A satisfactory theoretical characterization of deep learning however, is…
Theory III: Dynamics and Generalization in Deep Networks
Andrzej Banburski, Qianli Liao, Brando Miranda +4
The key to generalization is controlling the complexity of the network. However, there is no obvious control of complexity -- such as an explicit regularization term -- in the trai…
A Surprising Linear Relationship Predicts Test Performance in Deep Networks
Qianli Liao, Brando Miranda, Andrzej Banburski +2
Given two networks with the same training loss on a dataset, when would they have drastically different test losses and errors? Better understanding of this question of generalizat…
Theory IIIb: Generalization in Deep Networks
Tomaso Poggio, Qianli Liao, Brando Miranda +3
A main puzzle of deep neural networks (DNNs) revolves around the apparent absence of "overfitting", defined in this paper as follows: the expected error does not get worse when inc…