Blend beats using machine learning to create music in a fun new way.
-
Updated
Mar 27, 2018 - JavaScript
A variational autoencoder (VAE) is a generative model that combines deep learning with Bayesian inference to learn compact latent representations of data. VAEs are widely used for image generation, anomaly detection, and data augmentation.
Blend beats using machine learning to create music in a fun new way.
an interface for generating music with a VAE
Veeva Vault Approved Email package manager
Tiled VAE fix: run PrismML's Bonsai-Image 4B WebGPU at 512px+ on GPUs without shader-f16 (GTX 10xx / Pascal & older). Root cause analysis + 1.4KB patch, no quality loss on f16 devices.
Schema-driven ML experimentation platform: visual graph editor, 51 live demo models across GANs, diffusion, VAEs, vision, NLP, and physics; runs in TF.js, PyTorch, and notebooks.