Comparison of the Application of FNN and LSTM Based on the Use of Modules of Artificial Neural Networks in Generating an Individual Knowledge Testing Trajectory
Bibliographic record
Abstract
The paper considers the issues of implementing an adaptive testing system using artificial neural network modules, which should resolve the problem of intellectual selection of the next questions, thereby generating an individual testing strategy. An attempt is made to increase the accuracy of the artificial neural network in determining the level of difficulty of the next test question for two types of architectures -Feedforward Neural Network (FNN) and Long-Short Term Memory (LSTM) network. Parameters affecting the quality of education are analyzed. A modification of the input layer architecture of the FNN that allows for a significant increase in the accuracy of the networks is reviewed. To solve the problem of selecting the thematic block of the question, a hybrid module structure comprising the artificial neural network together with the algorithmic processing of the results it delivers is proposed. The feasibility of using an FNN compared to the LSTM network architecture is substantiated. The network input parameters are identified, and different architectures and network training parameters (weight update algorithms, loss functions, number of training epochs, packet size) are compared. The use of the FNN direct propagation network as part of a hybrid algorithmic module makes it possible to construct a trajectory with an individual testing length, regardless of the number of thematic blocks.
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 | 0.002 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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".