A lot of papers talk about tuning #autoencoder bottlenecks. Is there some autoencoder-like technique that share's #PCA's property of putting the most relevant information in the first element, second most in the second, etc?

A simple, efficient and scalable contrastive masked autoencoder for learning visual representations

https://openreview.net/forum?id=pjdxPts6er

#autoencoders #autoencoder #imagenet

Extremely proud to present my group's pre-print paper executed by my PhD student Mr. Jonas Köhler on #earthquake #forecasting using #deeplearning. We pose earthquake forecasting as a classification problem and train a Neural Network to decide, whether a #timeseries of length greater than 2 years will end in an earthquake on the following day with magnitude greater than 5 or not. The study could be summarised in following three points: 1) We use spatio-temporal b value data, on which we train an #autoencoder to learn the normal seismic behaviour. 2) We then take the pixel by pixel reconstruction error as input for a Convolutional Dilated Network classifier, whose model output could serve for earthquake forecasting. 3) We develop a special progressive training method for this model to mimic real life use. #data #research #ai4good #ai4science #seismology
https://arxiv.org/abs/2307.01812

A Latent Diffusion Model for Protein Structure Generation

https://openreview.net/forum?id=8zzjemksJd

#proteins #autoencoder #protein

What is DALL-E, and how does it work? - Discover the process of text-to-image synthesis using DALL-E’s au... - https://cointelegraph.com/news/what-is-dall-e-and-how-does-it-work #text-to-imagesynthesis #imagegeneration #generativeai #deeplearning #autoencoder #dall-e

CAE v2: Context Autoencoder with CLIP Latent Alignment

https://openreview.net/forum?id=f36LaK7M0F

#autoencoder #encoder #masked

"Diffusion language models" blog post by @sedielem - lots of illuminating details, e.g. the connection between diffusion noise levels and scale (frequency) of features https://benanne.github.io/2023/01/09/diffusion-language.html #AI #deeplearning #diffusion #autoencoder

'Cauchy–Schwarz Regularized Autoencoder', by Linh Tran, Maja Pantic, Marc Peter Deisenroth.

http://jmlr.org/papers/v23/21-0681.html

#autoencoders #autoencoder #generative

#arxivfeed :

"GD-VAEs: Geometric Dynamic Variational Autoencoders for Learning Nonlinear Dynamics and Dimension Reductions"
https://arxiv.org/abs/2206.05183

#MachineLearning #DeepLearning #Variational #Autoencoder #DynamicalSystems

#arxivfeed :

"Auto-Encoding Variational Bayes"
https://arxiv.org/abs/1312.6114

#MachineLearning #VariationalBayes #Bayesian #Inference #ProbabilisticModel #AutoEncoder #DeepLearning

"Unsupervised segmentation of biomedical hyperspectral image data: tackling high dimensionality with convolutional autoencoders"
Biomedical Optics Express Vol. 13, Issue 12, pp. 6373-6388 (2022)
https://doi.org/10.1364/BOE.476233
#autoencoder #deeplearning #ml #openaccess

Wrote a short overview of autoencoders and how they compare to diffusers, especially the denoising variants.

#autoencoder #diffusion

https://eugeneyan.com/writing/autoencoders-vs-diffusers/

machinic orderings flowing from unconditional generation, a model trained on 3+ hours of my music for strings, using RAVE (Real-time Audio Variational autoEncoder) released by the IRCAM and running in the nn~ externals in Max/MSP

I can sometimes catch a glimpse of a musical gesture i created, but mostly it’s a surprising and fertile stream of endless (algorithmic) melody

https://www.youtube.com/watch?v=S1gEQy4XFec

#machinelearning #RAVE #autoencoder #aimusic #python #maxmsp #composer #gavcloud

Entrenando a #CUT para hacer gatos enojados.
Parece que entrena más rápido que #cycleGAN

Quiero aprender con ejemplos fáciles de modificar lástima que la mayoría de los #autoencoder son muy monolíticos (usan npz) y no explican como armar los tuyos propios