teo-sl/DPLAN_pytorch
This repository contains an implementation of an anomaly detection method called DPLAN, which is based on the reinforcement learning framework. The method is described in the paper "Toward Deep Supervised Anomaly Detection: Reinforcement Learning from Partially Labeled Anomaly Data" by Pang et al.
This helps you identify unusual patterns or outliers in your data, even when you only have a few examples of what's normal or anomalous. You provide your dataset, and it flags the data points that are most likely to be anomalies. This is for data analysts, security professionals, or operations managers who need to detect rare but critical events.
No commits in the last 6 months.
Use this if you need to find anomalies in large datasets where only some data points are labeled as normal or anomalous, and traditional methods aren't precise enough.
Not ideal if you have a perfectly labeled dataset with clear examples of all normal and anomalous cases, as simpler supervised methods might suffice.
Stars
12
Forks
2
Language
Python
License
MIT
Category
Last pushed
Jan 08, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/teo-sl/DPLAN_pytorch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
yzhao062/pyod
A Python Library for Outlier and Anomaly Detection, Integrating Classical and Deep Learning Techniques
unit8co/darts
A python library for user-friendly forecasting and anomaly detection on time series.
elki-project/elki
ELKI Data Mining Toolkit
raphaelvallat/antropy
AntroPy: entropy and complexity of (EEG) time-series in Python
Minqi824/ADBench
Official Implement of "ADBench: Anomaly Detection Benchmark", NeurIPS 2022.