Introduction

This repository contains the code to perform Complex Event Processing (CEP) using an event calculus approach in DeepProbLog.

The implementation for the CEP with an event calculus approach is inspired by the paper A Probabilistic Logic Programming Event Calculus.

The code for DeepProbLog has slightly modified from the original source, presented in the paper DeepProbLog: Neural Probabilistic Logic Programming in the following ways:

Slight changes on how the training of the neural network is performed.
Code has been added to perform CEP on:
- MNIST digits (the code can be found here)
- Urban Sounds 8K (the code can be found here)

DeepProbLog

DeepProbLog is an extension of ProbLog that integrates Probabilistic Logic Programming with Deep Learning. See our paper on DeepProbLog.

DeepProbLog has the following requirements:

DeepProbLog comes with a few examples:

Name		Name	Last commit message	Last commit date
Latest commit History 25 Commits
examples/NIPS		examples/NIPS
test		test
.gitignore		.gitignore
LICENSE		LICENSE
README.md		README.md
Untitled.ipynb		Untitled.ipynb
__init__.py		__init__.py
data_loader.py		data_loader.py
gradient_semiring.py		gradient_semiring.py
in_out.py		in_out.py
logger.py		logger.py
logic.py		logic.py
model.py		model.py
network.py		network.py
optimizer.py		optimizer.py
standard_networks.py		standard_networks.py
test_utils.py		test_utils.py
train.py		train.py
vector_shape.py		vector_shape.py