arranger1044/spae
Code and supplemental material for "Sum-Product Autoencoding: Encoding and Decoding Representations using Sum-Product Networks"
This project helps researchers and data scientists better understand and represent complex data, especially for multi-label classification tasks. It takes structured, often binarized, datasets (like image features or text data) and uses Sum-Product Networks (SPNs) to create new, more insightful data representations, or 'embeddings'. These embeddings can then be used for tasks like image recognition, text analysis, or other pattern recognition challenges.
No commits in the last 6 months.
Use this if you are a machine learning researcher or data scientist working with multi-label datasets and want to explore novel methods for unsupervised data representation learning.
Not ideal if you are looking for a plug-and-play solution for general deep learning tasks without a background in probabilistic graphical models or representation learning theory.
Stars
8
Forks
1
Language
Python
License
GPL-3.0
Category
Last pushed
Dec 01, 2017
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/arranger1044/spae"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
MilaNLProc/contextualized-topic-models
A python package to run contextualized topic modeling. CTMs combine contextualized embeddings...
vinid/cade
Compass-aligned Distributional Embeddings. Align embeddings from different corpora
spcl/ncc
Neural Code Comprehension: A Learnable Representation of Code Semantics
criteo-research/CausE
Code for the Recsys 2018 paper entitled Causal Embeddings for Recommandation.
vintasoftware/entity-embed
PyTorch library for transforming entities like companies, products, etc. into vectors to support...