Publication

Jamming transition as a paradigm to understand the loss landscape of deep neural networks

Related publications (133)

Graph Chatbot

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

PyBrain

Yi Sun, Daniël Pieter Wierstra, Tom Schaul

PyBrain is a versatile machine learning library for Python. Its goal is to provide flexible, easy-to-use yet still powerful algorithms for machine learning tasks, including a variety of predefined environments and benchmarks to test and compare algorithms. ...

Massachusetts Institute of Technology Press2010

Hierarchical Multilayer Perceptron based Language Identification

Hervé Bourlard, David Imseng

Automatic language identification (LID) systems generally exploit acoustic knowledge, possibly enriched by explicit language specific phonotactic or lexical constraints. This paper investigates a new LID approach based on hierarchical multilayer perceptron ...

Idiap2010

Culture, gaze and the neural processing of fear expressions

Nouchine Hadjikhani

The direction of others' eye gaze has important influences on how we perceive their emotional expressions. Here, we examined differences in neural activation to direct-versus averted-gaze fear faces as a function of culture of the participant (Japanese ver ...

2010

Hierarchical Multilayer Perceptron based Language Identification

Hervé Bourlard, David Imseng

2010

Floor Holder Detection and End of Speaker Turn Prediction in Meetings

Hervé Bourlard

We propose a novel fully automatic framework to detect which meeting participant is currently holding the conversational floor and when the current speaker turn is going to finish. Two sets of experiments were conducted on a large collection of multiparty ...

ISCA2010

Improving Face Authetication Using Virtual Samples

Sébastien Marcel, Samy Bengio, Norman Hoon Thian Poh

In this paper, we present a simple yet effective way to improve a face verification system by generating multiple virtual samples from the unique image corresponding to an access request. These images are generated using simple geometric transformations. T ...

2003

Improving Face Authetication Using Virtual Samples

Sébastien Marcel, Samy Bengio, Norman Hoon Thian Poh

IDIAP2002

Optimization of high order perceptrons

Neural networks are widely applied in research and industry. However, their broader application is hampered by various technical details. Among these details are several training parameters and the choice of the topology of the network. The subject of this ...

École Polytechnique Fédérale de Lausanne1997

Optimization of high order perceptrons

EPFL1997

Optimal Setting of Weights, Learning Rate, and Gain

The optimal setting of the initial weights, learning rate, and gain of the activation function, which are key parameters of a neural network, influencing training time and generalization performance, are investigated by means of a large number of experimen ...

IDIAP1997