Ecosyste.ms: Repos

An open API service providing repository metadata for many open source software ecosystems.

GitHub topics: neuro-symbolic-learning

Repositories

ccclyu/awesome-deeplogic

A collection of papers of neural-symbolic AI (mainly focus on NLP applications)

Size: 66.4 KB - Last synced: 22 days ago - Pushed: 3 months ago - Stars: 200 - Forks: 25

MNoorFawi/pytholog

Python library that enables using prolog syntax and logic programming in python

Language: Python - Size: 5.42 MB - Last synced: 22 days ago - Pushed: over 1 year ago - Stars: 105 - Forks: 16

AIKA is a new type of artificial neural network designed to more closely mimic the behavior of a biological brain and to bridge the gap to classical AI. A key design decision in the Aika network is to conceptually separate the activations from their neurons, meaning that there are two separate graphs. One graph consisting of neurons and synapses representing the knowledge the network has already acquired and another graph consisting of activations and links describing the information the network was able to infer about a concrete input data set. There is a one-to-many relation between the neurons and the activations. For example, there might be a neuron representing a word or a specific meaning of a word, but there might be several activations of this neuron, each representing an occurrence of this word within the input data set. A consequence of this decision is that we have to give up on the idea of a fixed layered topology for the network, since the sequence in which the activations are fired depends on the input data set. Within the activation network, each activation is grounded within the input data set, even if there are several activations in between. This means links between activations serve two purposes. On the one hand, they are used to sum up the synapse weights and, on the other hand they propagate the identity to higher level activations.

Language: Java - Size: 12.5 MB - Last synced: about 2 months ago - Pushed: about 2 months ago - Stars: 70 - Forks: 19

hriaz17/ELLEN

Code for "ELLEN: Extremely Lightly Supervised Learning For Efficient Named Entity Recognition" (LREC-COLING 2024)

Size: 884 KB - Last synced: about 1 month ago - Pushed: about 1 month ago - Stars: 1 - Forks: 0

MahmudulAlam/Holographic-Reduced-Representations

Holographic Reduced Representations

Language: Python - Size: 329 KB - Last synced: 9 days ago - Pushed: 12 months ago - Stars: 19 - Forks: 2

google/neural-logic-machines 📦

Implementation for the Neural Logic Machines (NLM).

Language: Python - Size: 644 KB - Last synced: about 1 month ago - Pushed: about 5 years ago - Stars: 277 - Forks: 48

lucidrains/ESBN-pytorch

Usable implementation of Emerging Symbol Binding Network (ESBN), in Pytorch

Language: Python - Size: 64.5 KB - Last synced: 9 days ago - Pushed: over 3 years ago - Stars: 24 - Forks: 2

AbductiveLearning/ABLkit

An efficient Python toolkit for Abductive Learning (ABL), a novel paradigm that integrates machine learning and logical reasoning in a unified framework.

Language: Python - Size: 9.07 MB - Last synced: 20 days ago - Pushed: 3 months ago - Stars: 24 - Forks: 1

nerdimite/neuro-symbolic-ai-soc

Neuro-Symbolic Visual Question Answering on Sort-of-CLEVR using PyTorch

Language: Jupyter Notebook - Size: 8.99 MB - Last synced: about 2 months ago - Pushed: over 2 years ago - Stars: 52 - Forks: 13

lucidrains/esbn-transformer

An attempt to merge ESBN with Transformers, to endow Transformers with the ability to emergently bind symbols

Language: Python - Size: 5.86 KB - Last synced: about 1 month ago - Pushed: almost 3 years ago - Stars: 15 - Forks: 1

Mehran-k/RelNN

RelNN is a novel first-order deep neural model for relational learning.

Language: Java - Size: 6.69 MB - Last synced: 8 months ago - Pushed: over 6 years ago - Stars: 26 - Forks: 3

HannaAbiAkl/PSYCHIC

The official repository for the PSYCHIC model

Language: Jupyter Notebook - Size: 609 KB - Last synced: 8 months ago - Pushed: 8 months ago - Stars: 0 - Forks: 0

vacancy/NSCL-PyTorch-Release

PyTorch implementation for the Neuro-Symbolic Concept Learner (NS-CL).

Language: Python - Size: 292 KB - Last synced: 8 months ago - Pushed: over 3 years ago - Stars: 393 - Forks: 91

ForoughA/recursiveMemNet

Tree Stack Memory Units

Language: Python - Size: 19 MB - Last synced: 10 months ago - Pushed: almost 4 years ago - Stars: 16 - Forks: 2

LGirrbach/Discrete-Latent-Representation

Implementation of a straight-through gradient wrapper to allow for discrete latent representations. Provides binary discretizer which maps hidden representations to {0, 1} and a learnable multi-value discretizer, which maps hidden activations to their closest value in a set of given size.

Language: Jupyter Notebook - Size: 5.86 KB - Last synced: 11 months ago - Pushed: over 1 year ago - Stars: 0 - Forks: 0