Publication

Learning and generation of slow sequences: an application to music composition

Related publications (35)

Algorithmic composition of melodies with deep recurrent neural networks

A big challenge in algorithmic composition is to devise a model that is both easily trainable and able to reproduce the long-range temporal dependencies typical of music. Here we investigate how artificial neural networks can be trained on a large corpus o ...

2016

Social LSTM: Human Trajectory Prediction in Crowded Spaces

Alexandre Massoud Alahi, Vignesh Ramanathan

Pedestrians follow different trajectories to avoid obstacles and accommodate fellow pedestrians. Any autonomous vehicle navigating such a scene should be able to foresee the future positions of pedestrians and accordingly adjust its path to avoid collision ...

IEEE2016

Music Learning with Long Short Term Memory Networks

Florian François Colombo

Humans are able to learn and compose complex, yet beautiful, pieces of music as seen in e.g. the highly complicated works of J.S. Bach. However, how our brain is able to store and produce these very long temporal sequences is still an open question. Long s ...

2015

Recurrent Convolutional Neural Networks for Scene Labeling

Ronan Collobert, Pedro Henrique Oliveira Pinheiro

The goal of the scene labeling task is to assign a class label to each pixel in an image. To ensure a good visual coherence and a high class accu- racy, it is essential for a model to capture long range (pixel) label dependencies in images. In a feed-forwa ...

2014

A bottom-up stochastic model to predict building occupants' time-dependent activities

Jean-Louis Scartezzini, Darren Robinson, Frédéric Haldi, Urs Wilke

A bottom-up modelling approach together with a set of calibration methodologies is presented to predict residential building occupants' time-dependent activities, for use in dynamic building simulations. The stochastic model to predict activity chains is c ...

Elsevier2013

Recurrent Convolutional Neural Networks for Scene Parsing

Ronan Collobert, Pedro Henrique Oliveira Pinheiro

Scene parsing is a technique that consist on giving a label to all pixels in an image according to the class they belong to. To ensure a good visual coherence and a high class accuracy, it is essential for a scene parser to capture image long range depende ...

Idiap2013

Conditional probabilities in the excursion set theory: generic barriers and non-Gaussian initial conditions

Andrea De Simone, Michele Maggiore

The excursion set theory, where density perturbations evolve stochastically with the smoothing scale, provides a method for computing the dark matter halo mass function. The computation of the mass function is mapped into the so-called first-passage time p ...

Blackwell Publishing Ltd, Oxford2011

Evolving Complete Robots with CPPN-NEAT: The Utility of Recurrent Connections

Joshua Evan Auerbach

This paper extends prior work using Compositional Pattern Producing Networks (CPPNs) as a generative encoding for the purpose of simultaneously evolving robot morphology and control. A method is presented for translating CPPNs into complete robots includin ...

ACM Press2011

Anthropic Correction of Information Estimates

Michael Christoph Gastpar

A novel estimator for mutual information is proposed. The estimator is useful for the (asymmetric) scenario where only a few samples for one random variable are available, but for each sample, the conditional distribution of the other random variable can b ...

Ieee Service Center, 445 Hoes Lane, Po Box 1331, Piscataway, Nj 08855-1331 Usa2009

Closed-form solutions to stochastic switching problems

Erwan Morellec

This paper studies the price of an asset depending on both a fundamental and possible interventions of an authority. Using the martingale approach in continuous time, we provide closed-form solutions to switching problems involving irreversible, state depe ...

2008

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.