Shane Storm Strachan | Searcharxiv

arXiv2023

Matrix Domination: Convergence of a Genetic Algorithm Metaheuristic with the Wisdom of Crowds to Solve the NP-Complete Problem

This research explores the application of a genetic algorithm metaheuristic enriched by the wisdom of crowds in order to address the NP-Complete matrix domination problem (henceforth: TMDP) which is itself a constraint on related problems applied in graphs. Matrix domination involves accurately placing a subset of cells, referred to as dominators, within a matrix with the goal of their dominating the remainder of the cells. This research integrates the exploratory nature of a genetic algorithm with the wisdom of crowds to find more optimal solutions with user-defined parameters to work within computational complexity considerations and gauge performance mainly with a fitness evaluation function and a constraining function to combat the stochastic nature of genetic algorithms. With this, I propose a novel approach to MDP with a genetic algorithm that incorporates the wisdom of crowds, emphasizing collective decision-making in the selection process, and by exploring concepts of matrix permutations and their relevance in finding optimal solutions. Results demonstrate the potential of this convergence to generate efficient solutions, optimizing the trade-off between the number of dominators and their strategic placements within the matrices while efficiently ensuring consistent and complete matrix domination.

cs.NE↗

arXiv2023

Finetuning an LLM on Contextual Knowledge of Classics for Q&A

The open-source publishing of large language models (LLMs) has created many possibilities for how anyone who understands language and has access to a computer can interact with significant tools of artificial intelligence, particularly in the context of learning and knowledge dissemination. However, the utility of these models in specialized fields like Classics is still largely unexplored. This project is an attempt to merge the knowledge of Classics with the capabilities of artificial intelligence by finetuning an LLM to cater to the specific needs of learners and professionals. The goal of this project is to develop an LLM that not only reproduces contextual knowledge accurately but also exhibits a consistent "personality" - and, indeed, has consistent propriety - to appeal to a diverse audience who possess differing levels of knowledge. A significant portion of this project was dedicated to refining the dataset, following the principle of "garbage in, garbage out," to ensure the model generates relevant, useful, and creative responses when given a prompt (a statement, question, or single word). After training and evaluation, my model's ability to handle a vast array of different types of inputs and prompting exceeded expectations for a 355M parameter model, though its occasional hallucinations (especially when set with a high temperature), particularly in its assertions about historical events or its own identity, make it seem somewhat capricious and more work in the form of continuous finetuning will be undertaken.

cs.CL↗