Python Heart Sound Data Compression
-
Updated
Aug 23, 2018 - Python
Python Heart Sound Data Compression
3-bit Lloyd-Max KV Cache Compression for LLM Inference on NVIDIA DGX Spark GB10 — 5.12x compression, 0.983 cosine similarity, pure numpy on ARM unified memory
Extends classical optimal quantization theory (Lloyd-Max, entropy-constrained VQ) to neural latent spaces with learned non-Gaussian distributions.
University Project for core course Digital Communications
Fast compressed ANN search via randomized Hadamard transform and optimal Gaussian scalar quantization. Pure NumPy.
Lloyd-Max scalar quantization implementation with distortion, MSE, SQNR analysis, tests, and visualized experiments.
To associate your repository with the lloyd-max topic, visit your repo's landing page and select "manage topics."