cambridge-mlg/convcnp
Implementation of the Convolutional Conditional Neural Process
This project helps machine learning researchers explore and reproduce experiments on Convolutional Conditional Neural Processes. It takes various synthetic 1D datasets, such as those generated by Gaussian Processes or sawtooth functions, and trains different neural process models on them. The output is the average log-likelihood, helping evaluate model performance on unseen data. Researchers in machine learning who work with probabilistic models and data imputation would find this useful.
129 stars. No commits in the last 6 months.
Use this if you are a machine learning researcher studying or implementing Conditional Neural Processes and want to reproduce 1D experimental results or compare different model architectures on synthetic datasets.
Not ideal if you need a tool for real-world data prediction or anomaly detection, as this is primarily an experimental framework for academic research.
Stars
129
Forks
19
Language
Jupyter Notebook
License
—
Category
Last pushed
May 17, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/cambridge-mlg/convcnp"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
pykt-team/pykt-toolkit
pyKT: A Python Library to Benchmark Deep Learning based Knowledge Tracing Models
microsoft/archai
Accelerate your Neural Architecture Search (NAS) through fast, reproducible and modular research.
google-research/morph-net
Fast & Simple Resource-Constrained Learning of Deep Network Structure
IDEALLab/EngiBench
Benchmarks for automated engineering design
AI-team-UoA/pyJedAI
An open-source library that leverages Python’s data science ecosystem to build powerful...