Search Results for author: Jean-Pascal Pfister

Found 10 papers, 3 papers with code

On gauge freedom, conservativity and intrinsic dimensionality estimation in diffusion models

no code implementations6 Feb 2024 Christian Horvat, Jean-Pascal Pfister

In the original formulation of the diffusion model, this vector field is assumed to be the score function (i. e. it is the gradient of the log-probability at a given time in the diffusion process).

Denoising Density Estimation

Efficient Sampling-Based Bayesian Active Learning for synaptic characterization

no code implementations19 Jan 2022 Camille Gontier, Simone Carlo Surace, Igor Delvendahl, Martin Müller, Jean-Pascal Pfister

Bayesian Active Learning (BAL) is an efficient framework for learning the parameters of a model, in which input stimuli are selected to maximize the mutual information between the observations and the unknown parameters.

Active Learning

Denoising Normalizing Flow

1 code implementation NeurIPS 2021 Christian Horvat, Jean-Pascal Pfister

Here we propose a novel method - called Denoising Normalizing Flow (DNF) - that estimates the density on the low-dimensional manifold while learning the manifold as well.

Denoising Density Estimation

Density estimation on low-dimensional manifolds: an inflation-deflation approach

2 code implementations25 May 2021 Christian Horvat, Jean-Pascal Pfister

We also show that, if the embedding dimension is much larger than the manifold dimension, noise in the normal space can be well approximated by Gaussian noise.

Density Estimation

The Hitchhiker's Guide to Nonlinear Filtering

1 code implementation21 Mar 2019 Anna Kutschireiter, Simone Carlo Surace, Jean-Pascal Pfister

From there we continue our journey through discrete-time models, which is usually encountered in machine learning, and generalize to and further emphasize continuous-time filtering theory.


Propagation of spiking moments in linear Hawkes networks

no code implementations18 Sep 2018 Matthieu Gilson, Jean-Pascal Pfister

The present paper provides exact mathematical expressions for the high-order moments of spiking activity in a recurrently-connected network of linear Hawkes processes.

Online Maximum Likelihood Estimation of the Parameters of Partially Observed Diffusion Processes

no code implementations1 Nov 2016 Simone Carlo Surace, Jean-Pascal Pfister

We revisit the problem of estimating the parameters of a partially observed diffusion process, consisting of a hidden state process and an observed process, with a continuous time parameter.

Synaptic plasticity as Bayesian inference

no code implementations4 Oct 2014 Laurence Aitchison, Jannes Jegminat, Jorge Aurelio Menendez, Jean-Pascal Pfister, Alex Pouget, Peter E. Latham

They then use that uncertainty to adjust their learning rates, with more uncertain weights having higher learning rates.

Bayesian Inference

Sequence learning with hidden units in spiking neural networks

no code implementations NeurIPS 2011 Johanni Brea, Walter Senn, Jean-Pascal Pfister

We consider a statistical framework in which recurrent networks of spiking neurons learn to generate spatio-temporal spike patterns.

Know Thy Neighbour: A Normative Theory of Synaptic Depression

no code implementations NeurIPS 2009 Jean-Pascal Pfister, Peter Dayan, Máté Lengyel

Synapses exhibit an extraordinary degree of short-term malleability, with release probabilities and effective synaptic strengths changing markedly over multiple timescales.

Cannot find the paper you are looking for? You can Submit a new open access paper.