Search Results for author: Botond Cseke

Found 15 papers, 1 papers with code

Guided Decoding for Robot Motion Generation and Adaption

no code implementations22 Mar 2024 Nutan Chen, Elie Aljalbout, Botond Cseke, Patrick van der Smagt

This integration facilitates rapid adaptation to new tasks and optimizes the utilization of accumulated expertise by allowing robots to learn and generalize from demonstrated trajectories.

Local Distance Preserving Auto-encoders using Continuous k-Nearest Neighbours Graphs

no code implementations13 Jun 2022 Nutan Chen, Patrick van der Smagt, Botond Cseke

Auto-encoder models that preserve similarities in the data are a popular tool in representation learning.

Representation Learning

Latent Matters: Learning Deep State-Space Models

no code implementations NeurIPS 2021 Alexej Klushyn, Richard Kurle, Maximilian Soelch, Botond Cseke, Patrick van der Smagt

Our results show that the constrained optimisation framework significantly improves system identification and prediction accuracy on the example of established state-of-the-art DSSMs.

Variational Inference

Constrained Probabilistic Movement Primitives for Robot Trajectory Adaptation

no code implementations29 Jan 2021 Felix Frank, Alexandros Paraschos, Patrick van der Smagt, Botond Cseke

We unify previous adaptation techniques, for example, various types of obstacle avoidance, via-points, mutual avoidance, in one single framework and combine them to solve complex robotic problems.

Robotics

Continual Learning with Bayesian Neural Networks for Non-Stationary Data

no code implementations ICLR 2020 Richard Kurle, Botond Cseke, Alexej Klushyn, Patrick van der Smagt, Stephan Günnemann

We represent the posterior approximation of the network weights by a diagonal Gaussian distribution and a complementary memory of raw data.

Continual Learning

Increasing the Generalisation Capacity of Conditional VAEs

no code implementations23 Aug 2019 Alexej Klushyn, Nutan Chen, Botond Cseke, Justin Bayer, Patrick van der Smagt

We address the problem of one-to-many mappings in supervised learning, where a single instance has many different solutions of possibly equal cost.

Structured Prediction

Learning Hierarchical Priors in VAEs

no code implementations NeurIPS 2019 Alexej Klushyn, Nutan Chen, Richard Kurle, Botond Cseke, Patrick van der Smagt

We propose to learn a hierarchical prior in the context of variational autoencoders to avoid the over-regularisation resulting from a standard normal prior distribution.

Efficient Low-Order Approximation of First-Passage Time Distributions

no code implementations1 Jun 2017 David Schnoerr, Botond Cseke, Ramon Grima, Guido Sanguinetti

We consider the problem of computing first-passage time distributions for reaction processes modelled by master equations.

Bayesian Inference Sequential Bayesian Inference

f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization

2 code implementations NeurIPS 2016 Sebastian Nowozin, Botond Cseke, Ryota Tomioka

Generative neural samplers are probabilistic models that implement sampling using feedforward neural networks: they take a random input vector and produce a sample from a probability distribution defined by the network weights.

Expectation propagation for continuous time stochastic processes

no code implementations18 Dec 2015 Botond Cseke, David Schnoerr, Manfred Opper, Guido Sanguinetti

We consider the inverse problem of reconstructing the posterior measure over the trajec- tories of a diffusion process from discrete time observations and continuous time constraints.

Properties of Bethe Free Energies and Message Passing in Gaussian Models

no code implementations16 Jan 2014 Botond Cseke, Tom Heskes

We define the Gaussian fractional Bethe free energy in terms of the moment parameters of the approximate marginals, derive a lower and an upper bound on the fractional Bethe free energy and establish a necessary condition for the lower bound to be bounded from below.

Approximate inference in latent Gaussian-Markov models from continuous time observations

no code implementations NeurIPS 2013 Botond Cseke, Manfred Opper, Guido Sanguinetti

We propose an approximate inference algorithm for continuous time Gaussian-Markov process models with both discrete and continuous time likelihoods.

Sparse Approximate Inference for Spatio-Temporal Point Process Models

no code implementations17 May 2013 Botond Cseke, Andrew Zammit Mangion, Tom Heskes, Guido Sanguinetti

Spatio-temporal point process models play a central role in the analysis of spatially distributed systems in several disciplines.

Factored expectation propagation for input-output FHMM models in systems biology

no code implementations17 May 2013 Botond Cseke, Guido Sanguinetti

We consider the problem of joint modelling of metabolic signals and gene expression in systems biology applications.

Variational Inference

Bayesian Source Localization with the Multivariate Laplace Prior

no code implementations NeurIPS 2009 Marcel V. Gerven, Botond Cseke, Robert Oostenveld, Tom Heskes

We introduce a novel multivariate Laplace (MVL) distribution as a sparsity promoting prior for Bayesian source localization that allows the specification of constraints between and within sources.

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