منابع مشابه
Autoencoding topology
The problem of learning a manifold structure on a dataset is framed in terms of a generative model, to which we use ideas behind autoencoders (namely adversarial/Wasserstein autoencoders) to fit deep neural networks. From a machine learning perspective, the resulting structure, an atlas of a manifold, may be viewed as a combination of dimensionality reduction and “fuzzy” clustering.
متن کاملStudy of carpinus betulus dieback distribution using topographic factors
The expanding phenomenon of dieback is caused by the reaction of trees against the harmful biotic and a biotic factor that lead to dying of shoots and branches of trees from upper crown to lower crown. This phenomenon spreads throughout the leaves and branches and all parts of the plant and may finally lead to the death of the plant. This study aimed to identify species dieback especially Carpi...
متن کاملImage Restoration using Autoencoding Priors
We propose to leverage denoising autoencoder networks as priors to address image restoration problems. We build on the key observation that the output of an optimal denoising autoencoder is a local mean of the true data density, and the autoencoder error (the difference between the output and input of the trained autoencoder) is a mean shift vector. We use the magnitude of this mean shift vecto...
متن کاملTemporal Autoencoding Restricted Boltzmann Machine
Much work has been done refining and characterizing the receptive fields learned by deep learning algorithms. A lot of this work has focused on the development of Gabor-like filters learned when enforcing sparsity constraints on a natural image dataset. Little work however has investigated how these filters might expand to the temporal domain, namely through training on natural movies. Here we ...
متن کاملAutoencoding Time Series for Visualisation
We present an algorithm for the visualisation of time series. To that end we employ echo state networks to convert time series into a suitable vector representation which is capable of capturing the latent dynamics of the time series. Subsequently, the obtained vector representations are put through an autoencoder and the visualisation is constructed using the activations of the “bottleneck”. T...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Journal of Computational Biology
سال: 2019
ISSN: 1557-8666
DOI: 10.1089/cmb.2018.0176