179Injecting uniform chaotic sequences into an ANN’s learning fabric to reduce overfitting
Bibliographic record
Abstract
Overfitting is a common problem in artificial neural networks (ANNs). Overfitting in ANNs arises because the capacity of the learner is much higher than that required by the dataset: having too many hidden layers or neurons, too many learning cycles, or too high of a degree of nonlinearity in the cost function will cause overfitting overfitting . The problem is that the required amount of capacity is generally not known a priori, and practitioners usually design with a very large capacity and then apply mitigation techniques, such as regularization, early stopping, pruning, and noise injection. Chaos injection is one of the effective solutions to prevent overfitting in ANNs. This chapter presents an improved chaotic chaotic map injection technique utilizing the enhanced multiparametric tent map (MTM multiparametric tent map (MTM) ). Our investigation found that better results were achieved when the chaotic chaotic map values had a uniform distribution. Accordingly, we choose a set of control parameters of the tent map that yielded the highest degree of uniformity according to the Kolmogorov-Smirnov Kolmogorov-Smirnov (KS) measure. Furthermore, we generated and processed the chaotic chaotic map values offline to avoid the problem of the initial values of the tent map undoing the desired uniform distribution. We generated all the sequences before training time using the MTM multiparametric tent map (MTM) based on dataset size, number of neurons in each layer, batch size, and number of k -folds. Next, we normalized the sequences through a novel chaotic chaotic map -sequence normalization and probability mass function equalization procedure to ensure they were uniform. Finally, we stored the uniformly distributed chaotic chaotic map values in a table. During training, the uniform sequences were read from the table and injected into the learning fabric of the ANN artificial neural network (ANN) . The experimental results demonstrate a superior accuracy of our proposed scheme in comparison with the latest techniques according to the following performance metrics: accuracy accuracy (ACC) , F 1 F 1-score ( F 1) -score F 1-score ( F 1) , negative predictive value negative predictive value (NPV) , positive predictive value positive predictive value (PPV) , sensitivity sensitivity (SN) , and specificity.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.005 | 0.001 |
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".