meowoodie/Neural-Spectral-Marked-Point-Processes
A novel general non-stationary point process model based on neural networks.
This project helps data scientists and researchers model sequences of discrete events that occur over time, especially when the event patterns change and events have complex attributes. It takes event data (like earthquake timestamps with magnitudes, or crime incidents with types and locations) and outputs a model that can predict future event occurrences and characteristics. This is for professionals analyzing complex event streams in fields like seismology, urban planning, or risk assessment.
No commits in the last 6 months.
Use this if you need to predict future discrete events in a system where event patterns evolve over time and events carry rich, multi-dimensional information.
Not ideal if your event processes are consistently stationary (patterns don't change much over time) or if events have very simple, low-dimensional attributes.
Stars
11
Forks
3
Language
Jupyter Notebook
License
—
Category
Last pushed
Sep 23, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/meowoodie/Neural-Spectral-Marked-Point-Processes"
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
AI-team-UoA/pyJedAI
An open-source library that leverages Python’s data science ecosystem to build powerful...
IDEALLab/EngiBench
Benchmarks for automated engineering design