Publications related to Loss landscape and symmetries in Neural Networks

Weakly-Supervised Concept-based Adversarial Learning for Cross-lingual Word Embeddings

Distributed representations of words which map each word to a continuous vector have proven useful in capturing important linguistic information not only in a single language but also across different languages. Current unsupervised adversarial approaches ...

Association for Computational Linguistics2019

Reconstruction of Cloud Vertical Structure With a Generative Adversarial Network

Jussi Sakari Leinonen

We demonstrate the feasibility of solving atmospheric remote sensing problems with machine learning using conditional generative adversarial networks (CGANs), implemented using convolutional neural networks. We apply the CGAN to generating two-dimensional ...

AMER GEOPHYSICAL UNION2019

Bounding Inefficiency of Equilibria in Continuous Actions Games using Submodularity and Curvature

Maryam Kamgarpour, Andreas Krause

Games with continuous strategy sets arise in several machine learning problems (e.g. adversarial learning). For such games, simple no-regret learning algorithms exist in several cases and ensure convergence to coarse correlated equilibria (CCE). The effic ...

PMLR2019

A comparative study on network alignment techniques

Thanh Trung Huynh, Thành Tâm Nguyên, Chi Thang Duong

Network alignment is a method to align nodes that belong to the same entity from different networks. A well-known application of network alignment is to map user accounts from different social networks that belong to the same person. As network alignment h ...

PERGAMON-ELSEVIER SCIENCE LTD2019

Learning embeddings: efficient algorithms and applications

Cijo Jose

Learning to embed data into a space where similar points are together and dissimilar points are far apart is a challenging machine learning problem. In this dissertation we study two learning scenarios that arise in the context of learning embeddings and o ...

École Polytechnique Fédérale de Lausanne2018

Learning embeddings: efficient algorithms and applications

Cijo Jose

Learning to embed data into a space where similar points are together and dissimilar points are far apart is a challenging machine learning problem. In this dissertation we study two learning scenarios that arise in the context of learning embeddings and o ...

EPFL2018

Computational Aesthetics and Image Enhancements using Deep Neural Networks

Bin Jin

Imaging devices have become ubiquitous in modern life, and many of us capture an increasing number of images every day. When we choose to share or store some of these images, our primary selection criterion is to choose the most visually pleasing ones. Yet ...

EPFL2018

Deep convolutional neural networks for estimating porous material parameters with ultrasound tomography

Jan Sickmann Hesthaven

We study the feasibility of data based machine learning applied to ultrasound tomography to estimate water-saturated porous material parameters. In this work, the data to train the neural networks is simulated by solving wave propagation in coupled porovis ...

2018

The committee machine: Computational to statistical gaps in learning a two-layers neural network

Nicolas Macris, Florent Gérard Krzakala, Lenka Zdeborová, Jean François Emmanuel Barbier

Heuristic tools from statistical physics have been used in the past to locate the phase transitions and compute the optimal learning and generalization errors in the teacher-student scenario in multi-layer neural networks. In this contribution, we provide ...

NEURAL INFORMATION PROCESSING SYSTEMS (NIPS)2018

SparseFool: a few pixels make a big difference

Pascal Frossard, Seyed Mohsen Moosavi Dezfooli, Apostolos Modas

Deep Neural Networks have achieved extraordinary results on image classification tasks, but have been shown to be vulnerable to attacks with carefully crafted perturbations of the input data. Although most attacks usually change values of many image's pixe ...

2018

Loss landscape and symmetries in Neural Networks

Weakly-Supervised Concept-based Adversarial Learning for Cross-lingual Word Embeddings

Bounding Inefficiency of Equilibria in Continuous Actions Games using Submodularity and Curvature

A comparative study on network alignment techniques

Deep convolutional neural networks for estimating porous material parameters with ultrasound tomography

Graph Chatbot

Chat with Graph Search

Weakly-Supervised Concept-based Adversarial Learning for Cross-lingual Word Embeddings

Reconstruction of Cloud Vertical Structure With a Generative Adversarial Network

Bounding Inefficiency of Equilibria in Continuous Actions Games using Submodularity and Curvature

A comparative study on network alignment techniques

Learning embeddings: efficient algorithms and applications

Learning embeddings: efficient algorithms and applications

Computational Aesthetics and Image Enhancements using Deep Neural Networks

Deep convolutional neural networks for estimating porous material parameters with ultrasound tomography

The committee machine: Computational to statistical gaps in learning a two-layers neural network

SparseFool: a few pixels make a big difference

Reconstruction of Cloud Vertical Structure With a Generative Adversarial Network

Computational Aesthetics and Image Enhancements using Deep Neural Networks

The committee machine: Computational to statistical gaps in learning a two-layers neural network

SparseFool: a few pixels make a big difference

Learning embeddings: efficient algorithms and applications

Learning embeddings: efficient algorithms and applications