A sampling-based approach for efficient clustering in large datasets
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 …
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 …
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 …
posterior distributions. Truncated distributions are proportional to exact posteriors within …
Direct evolutionary optimization of variational autoencoders with binary latents
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 …
models such as variational autoencoders (VAEs) with binary latents consequently became …
Efficient spatio-temporal feature clustering for large event-based datasets
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 …
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 …
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 …
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 …
variety of tasks, such as missing value estimation, denoising, clustering, outlier detection, or …
[CITA][C] Truncated Variational Expectation Maximization
J Lücke - arxiv, 2017