Interpretable Latent Spaces Using Space-Filling Vector Quantization

A new unsupervised method that combines two concepts of vector quantization and space-filling curves to interpret the latent space of DNNs

This post is a short explanation of our novel unsupervised distribution modeling technique called space-filling vector quantization [1] published at Interspeech 2023 conference. For more details, please look at the paper under this link.Image from StockSnap.io

Deep generative models are well-known neural network-based architectures that learn a latent space whose samples can be mapped to sensible real-world data …

deep-neural-networks interpretable ai latent-space