A Combined Finite State Machine and PlantUML Approach to Machine Learning Applications
Bibliographic record
Abstract
Despite recent progress made in the theory and practice of Artificial Intelligence (AI), there is still a lack of tools and algorithms for the design and implementation of Neural Networks (NN) capable of explaining how the processes producing decisions are made. Therefore there is a need for devising new algorithms for endowing NN to address the transparency and accountancy in the use of AI, especially in areas where AI decisions have a significant impact on people’s lives. This led to the research and investigation of algorithms for explainable AI (XAI), a field which is at the very beginning of its activities. In this paper, a Finite State Machine (FSM) approach is applied to the design and implementation of a blend of Machine Learning (ML) frameworks capable to auto-build, auto-train, and auto-deploy AI models using abstract representations. It is demonstrated, in this paper, that FSMs can be generated and applied at the design of engineering and AI automation tools such that platforms such as AutoML, AutoGluon and others can be controlled at their turn. The automation of AI models is achieved by parsing the FSM states, which results in the creation of Python artifacts that can be executed. The proposed FSM controls the Automated AI Platforms (AAIP) based on the decisions made by the FSM Controller (FSMC). The FSMC is the root of the FSM graph possessing in its structure the rules driving the NNs. The parsed diagrams are nodes of the diagrammatic reasoning (DR) algorithms. These algorithms are capable of selecting the proper FSM and PlantUML diagrams from a database of such diagrams. An implementation of the combination of FSM, FSMC and RNN is described in this paper plainly illustrating the advantages of the FSM approach to AI. The PlantUML diagrams used to generate the figures in this article can be found at the following URL1.1https://github.com/mirceat/FSM2ML-diagrams
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.008 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".