Name: Dirk Roeckmann
Type: User
Bio: Computer Scientist, IT Manager, Consultant, SAP Expert,
Independent AI Researcher,
AI = Deep Learning + Symbol Manipulation, Deep Quadric Learning
Twitter: fivetroop
Location: Pittsburgh
Dirk Roeckmann's Projects
Solve the multi-digit MNIST octal-division task, which requires the integration of high-level reasoning and low-level perception, by employing DeepProbLog.
A Machine Learning framework from scratch in Pure Mojo 🔥
Causal Inference and Discovery in Python by Packt Publishing
Causal Discovery in Python. It also includes (conditional) independence tests and score functions.
An experimental language for causal reasoning
Deep Quadric Learning
DeepProbLog is an extension of ProbLog that integrates Probabilistic Logic Programming with deep learning by introducing the neural predicate.
[Experimental] Global causal discovery algorithms
DoWhy is a Python library for causal inference that supports explicit modeling and testing of causal assumptions. DoWhy is based on a unified language for causal inference, combining causal graphical models and potential outcomes frameworks.
ALICE (Automated Learning and Intelligence for Causation and Economics) is a Microsoft Research project aimed at applying Artificial Intelligence concepts to economic decision making. One of its goals is to build a toolkit that combines state-of-the-art machine learning techniques
A simple probabilistic programming language.
This repository describes the governance model for the PyWhy org
JupyterLab desktop application, based on Electron.
Deep Learning for humans
Keras documentation, hosted live at keras.io
NCS AI - Intersection of neural, causal and symbolic paradigms
Probabilistic programming with NumPy powered by JAX for autograd and JIT compilation to GPU/TPU/CPU.
ProbLog is a Probabilistic Logic Programming Language for logic programs with probabilities.
Deep universal probabilistic programming with Python and PyTorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Experimental library integrating LLM capabilities to support causal analyses
Keep track of discussions and meeting minutes.
Python package for (conditional) independence testing and statistical functions related to causality.
Official Stanford NLP Python Library for Many Human Languages
You like pytorch? You like micrograd? You love tinygrad! ❤️