Deep residual autoencoder for reconstructing and analyzing spectral data using PyTorch. Includes composite loss, UMAP visualization, and spectral diagnostics. Built for unsupervised learning on high-dimensional spectra.
deep-learning pytorch autoencoder unsupervised-learning residual-network spectral-data latent-space spectral-reconstruction-umap torch-autoencoder
-
Updated
Aug 10, 2025 - Jupyter Notebook