A sampling-based approach for efficient clustering in large datasets

G Exarchakis, O Oubari, G Lenz - Proceedings of the IEEE …, 2022 - openaccess.thecvf.com
We propose a simple and efficient clustering method for high-dimensional data with a large
number of clusters. Our algorithm achieves high-performance by evaluating distances of …

Evolutionary variational optimization of generative models

J Drefs, E Guiraud, J Lücke - Journal of machine learning research, 2022 - jmlr.org
We combine two popular optimization approaches to derive learning algorithms for
generative models: variational optimization and evolutionary algorithms. The combination is …

Truncated variational expectation maximization

J Lücke - arxiv preprint arxiv:1610.03113, 2016 - arxiv.org
We derive a novel variational expectation maximization approach based on truncated
posterior distributions. Truncated distributions are proportional to exact posteriors within …

Direct evolutionary optimization of variational autoencoders with binary latents

J Drefs, E Guiraud, F Panagiotou, J Lücke - Joint European Conference on …, 2022 - Springer
Many types of data are generated at least partly by discrete causes. Deep generative
models such as variational autoencoders (VAEs) with binary latents consequently became …

Efficient spatio-temporal feature clustering for large event-based datasets

O Oubari, G Exarchakis, G Lenz… - Neuromorphic …, 2022 - iopscience.iop.org
Event-based cameras encode changes in a visual scene with high temporal precision and
low power consumption, generating millions of events per second in the process. Current …

Precise timing and computationally efficient learning in neuromorphic systems

O Oubari - 2020 - theses.hal.science
From image recognition to automated driving, machine learning nowadays is all around us
and impacts various aspects of our daily lives. This disruptive technology is rapidly evolving …

Evolutionary Variational Optimization of Generative Models

J Drefs, E Guiraud, J Lücke - arxiv preprint arxiv:2012.12294, 2020 - arxiv.org
We combine two popular optimization approaches to derive learning algorithms for
generative models: variational optimization and evolutionary algorithms. The combination is …

Evolutionary Variational Optimization for Probabilistic Unsupervised Learning

J Drefs - 2022 - oops.uni-oldenburg.de
Probabilistic generative modeling is a powerful machine learning paradigm suitable for a
variety of tasks, such as missing value estimation, denoising, clustering, outlier detection, or …

[CITA][C] Truncated Variational Expectation Maximization

J Lücke - arxiv, 2017