Optimizing the learning process of multi-layer perceptrons using a hybrid algorithm based on MVO and SA
Bibliographic record
Abstract
Artificial neural networks (ANNs) are one of the artificial intelligence techniques used in real-world problems and applications encountered in almost all industries such as education, health, chemistry, food, informatics, logistics, transportation. ANN is widely used in many techniques such as optimization, modelling, classification and forecasting, and many empirical studies have been carried out in areas such as planning, inventory management, maintenance, quality control, econometrics, supply chain management and logistics related to ANN. The most important and just as hard stage of ANNs is the learning process. This process is about finding optimal values in the search space for different datasets. In this process, the values generated by training algorithms are used as network parameters and are directly effective in the success of the neural network (NN). In classical training techniques, problems such as local optimum and slow convergence are encountered. Meta-heuristic algorithms for the training of ANNs in the face of this negative situation have been used in many studies as an alternative. In this study, a new hybrid algorithm namely MVOSANN is suggested for the training of ANNs, using Simulated annealing (SA) and Multi-verse optimizer (MVO) algorithms. The suggested MVOSANN algorithm has been experimented on 12 prevalently classification datasets. The productivity of MVOSANN has been compared with 12 well-recognized and current meta-heuristic algorithms. Experimental results show that MVOSANN produces very successful and competitive results.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.002 | 0.001 |
| 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".