PyNeuraLogic
hode
PyNeuraLogic | hode | |
---|---|---|
7 | 6 | |
267 | 143 | |
- | - | |
8.0 | 0.0 | |
6 days ago | almost 3 years ago | |
Python | Haskell | |
MIT License | GNU General Public License v3.0 only |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
PyNeuraLogic
-
[P] PyNeuraLogic - a framework for writing differentiable logic programs
Hi, sure. With this framework, you can write and train deep learning models similarly to PyTorch or TensorFlow. Although the main aim of PyNeuraLogic is on deep relational learning and it uses custom declarative language (implemented in Python). Best fitting use cases are everything where you can utilize relations. One of those use-cases that we are promoting right now is on Graph Neural Networks (GNNs), where you have relations between nodes (such as social networks, molecules). You can then utilize those relations and do regular tasks on graphs, such as link prediction, graph classification, node classification, etc. GNNs quite nicely fit the framework and its language and can be expressed just in one line (as shown in the README). The concrete use-case of PyNeuraLogic on GNNs could then be a molecule classification (example). Other use-cases could be for NLP (we have todo to write an example for it) or knowledge base completion. You could also use it like a regular framework without utilizing relations, but in that case, it might be more efficient to go with PyTorch or TensorFlow.
- Show HN: Evaluate Deep Learning models directly in a database with PyNeuraLogic
-
Why Hypergraphs? (2013)
For an original proposal that do logic inference on Hypergraphs I am using NeuraLogic, through a Python frontend (https://github.com/LukasZahradnik/PyNeuraLogic)
I wonder if this is something the author would have enjoyed…
-
This Week in Python
PyNeuraLogic – PyNeuraLogic lets you use Python to create Differentiable Logic Programs
- GitHub - LukasZahradnik/PyNeuraLogic: PyNeuraLogic lets you use Python to create Differentiable Logic Programs
- Show HN: PyNeuraLogic: Python Differentiable Logic Programs
hode
-
Why Hypergraphs? (2013)
I first heard of hypergraphs in the context of knowledge management using hode:
https://github.com/JeffreyBenjaminBrown/hode
I haven't looked more into them, but thought others might find hode interesting.
-
A tour to my Zettelkasten note clusters
It's an interesting idea. Maybe I should try. I suspect, though, that I want control over every node, no matter how general. The thing about my notes is they contain only information I think I might need. I have, for instance, an "emotions" node. I'm sure the Wikidata node for emotions is interesting, but I want my own node too.
I tried to square this circle once by writing Hode[1], which permits encoding certain data as relevant to me, and then filter my view accordingly when I wanted. But the encoding process (i.e. the user experience when adding data to one's knowledge base) was so hard that I gave up.
[1] https://github.com/JeffreyBenjaminBrown/hode
- Designing better file organization around tags, not hierarchies
-
PathQuery, Google's Graph Query Language
I wrote a language that's very close to natural language for writing to and querying a RSLT, a kind of higher order graph.
https://github.com/JeffreyBenjaminBrown/hode/blob/master/doc...
-
Ask HN: Who funds important tech with no business plan?
I know there are people with money who want to save the world. I think a higher-order knowledge base like Hode[1] could be useful in search, in AI, and in social networking. But I have no idea how to monetize it. It's more of a science project than a business. Am I out of luck until I do have such idea?
[1] https://github.com/JeffreyBenjaminBrown/hode
- Hode is- A Hypergraph Editor - JeffreyBenjaminBrown - GitHub
What are some alternatives?
reloadium - Hot Reloading and Profiling for Python
cotfs - FUSE filesystem based on tags
chemicalx - A PyTorch and TorchDrug based deep learning library for drug pair scoring. (KDD 2022)
TW5-TiddlyMap - Map drawing and topic visualization for your wiki
hatch - Modern, extensible Python project management
Camlistore - Perkeep (née Camlistore) is your personal storage system for life: a way of storing, syncing, sharing, modelling and backing up content.
pytorch_geometric - Graph Neural Network Library for PyTorch [Moved to: https://github.com/pyg-team/pytorch_geometric]
Second-Brain - A curated list of awesome Public Zettelkastens 🗄️ / Second Brains 🧠 / Digital Gardens 🌱
pygod - A Python Library for Graph Outlier Detection (Anomaly Detection)
logica - Logica is a logic programming language that compiles to SQL. It runs on Google BigQuery, PostgreSQL and SQLite.
gradio - Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!
ppfiletagger - file tagging and search by tag for Linux