116 citations · 1.1k across the 96 of their papers we have counts for
14 papers · 1 filter
Mathematics of Deep Learning
Rene Vidal, Joan Bruna, Raja Giryes +1
Recently there has been a dramatic increase in the performance of recognition systems due to the introduction of deep architectures for representation learning and classification.…
DeepRadiologyNet: Radiologist Level Pathology Detection in CT Head Images
Jameson Merkow, Robert Lufkin, Kim Nguyen +3
We describe a system to automatically filter clinically significant findings from computerized tomography (CT) head scans, operating at performance levels exceeding that of practic…
Block-Cyclic Stochastic Coordinate Descent for Deep Neural Networks
Kensuke Nakamura, Stefano Soatto, Byung-Woo Hong
We present a stochastic first-order optimization algorithm, named BCSC, that adds a cyclic constraint to stochastic block-coordinate descent. It uses different subsets of the data…
A Separation Principle for Control in the Age of Deep Learning
Alessandro Achille, Stefano Soatto
We review the problem of defining and inferring a "state" for a control system based on complex, high-dimensional, highly uncertain measurement streams such as videos. Such a state…
Critical Learning Periods in Deep Neural Networks
Alessandro Achille, Matteo Rovere, Stefano Soatto
Similar to humans and animals, deep artificial neural networks exhibit critical periods during which a temporary stimulus deficit can impair the development of a skill. The extent…
Stochastic gradient descent performs variational inference, converges to limit cycles for deep networks
Pratik Chaudhari, Stefano Soatto
Stochastic gradient descent (SGD) is widely believed to perform implicit regularization when used to train deep neural networks, but the precise manner in which this occurs has thu…
Parle: parallelizing stochastic gradient descent
Pratik Chaudhari, Carlo Baldassi, Riccardo Zecchina +3
We propose a new algorithm called Parle for parallel training of deep networks that converges 2-4x faster than a data-parallel implementation of SGD, while achieving significantly…
Emergence of Invariance and Disentanglement in Deep Representations
Alessandro Achille, Stefano Soatto
Using established principles from Statistics and Information Theory, we show that invariance to nuisance factors in a deep neural network is equivalent to information minimality of…
Deep Relaxation: partial differential equations for optimizing deep neural networks
Pratik Chaudhari, Adam Oberman, Stanley Osher +2
In this paper we establish a connection between non-convex optimization methods for training deep neural networks and nonlinear partial differential equations (PDEs). Relaxation te…
Classification regions of deep neural networks
Alhussein Fawzi, Seyed-Mohsen Moosavi-Dezfooli, Pascal Frossard +1
The goal of this paper is to analyze the geometric properties of deep neural network classifiers in the input space. We specifically study the topology of classification regions cr…
Adaptive Regularization of Some Inverse Problems in Image Analysis
Byung-Woo Hong, Ja-Keoung Koo, Martin Burger +1
We present an adaptive regularization scheme for optimizing composite energy functionals arising in image analysis problems. The scheme automatically trades off data fidelity and r…
Reinforced Temporal Attention and Split-Rate Transfer for Depth-Based Person Re-Identification
Nikolaos Karianakis, Zicheng Liu, Yinpeng Chen +1
We address the problem of person re-identification from commodity depth sensors. One challenge for depth-based recognition is data scarcity. Our first contribution addresses this p…
Robustness of classifiers to universal perturbations: a geometric perspective
Seyed-Mohsen Moosavi-Dezfooli, Alhussein Fawzi, Omar Fawzi +2
Deep networks have recently been shown to be vulnerable to universal perturbations: there exist very small image-agnostic perturbations that cause most natural images to be misclas…
Multi-Label Segmentation via Residual-Driven Adaptive Regularization
Byung-Woo Hong, Ja-Keoung Koo, Stefano Soatto
We present a variational multi-label segmentation algorithm based on a robust Huber loss for both the data and the regularizer, minimized within a convex optimization framework. We…