Allen Roush

CX_DB8. a contextual, biasable, word-or-sentence-or-paragraph extractive summarizer powered by the latest in text embeddings (Bert, Universal Sentence Encoder, Flair)

Constrained-Text-Generation-Studio. Code repo for "Most Language Models can be Poets too: An AI Writing Assistant and Constrained Text Generation Studio" at the (CAI2) workshop, jointly held at (COLING 2022)

Language-games. Dead simple games made with word vectors.

DebateSum. Corresponding code repo for the paper at COLING 2020 - ARGMIN 2020: "DebateSum: A large-scale argument mining and summarization dataset"

llm_steer-oobabooga. Steer LLM outputs towards a certain topic/subject and enhance response capabilities using activation engineering by adding steering vectors, now in oobabooga text generation webui!

Active-Explainable-Classification. A set of tools for leveraging pre-trained embeddings, active learning and model explainability for effecient document classification

Python-Cooperative-Synapse-NeuroEvolution. A Python implementation of the "CoSyne" algorithim, as described in this paper: https://pdfs.semanticscholar.org/966e/41903b4aff42601a188bd7b26d71ef120d11.pdf

python-neuroevolution. An implementation of "Conventional Neuroevolution" - evolving ANNs without backpropegation

DebateKG. Code Repo for the DebateGraph paper

Genetic-Algorithims-Python. Some fun code I wrote. One file does string matching and another one solves the Knapsack problem.

Bright. Measure how bright your github repo shines, and learn about interesting work that the people who were (or could have been) inspired by your repo have done

ECLAT-Association-Rule-Mining. An implementation of the Equivalence Class Transformation Association Rule Mining algorithim in Python

debate2vec. Word-vectors created from a large corpus of competative debate evidence

Hellisotherpeople.

DeepDebater. A Fully Automated and Choreographed Competitive Policy Debate System

Geist. A philosophy-inspired roguelike with Dijkstra-Maps and Unique Mechanics!

Simulated-Annealing-TSP-Numba. Using a metaheaurisitic technique called Simulated Annealing to solve the Traveling Salesman Problem.

llm_steer. Steer LLM outputs towards a certain topic/subject and enhance response capabilities using activation engineering by adding steering vectors