On Using Genetic Algorithm Optimized Activation Functions to Increase Neural Network Accuracy
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Neural Networks have been successfully applied to many problems throughout aerospace engineering. Such networks learn a training set by adjusting the weights assigned between connected pairs of neurons. Historically, optimization of the Neural Network’s input variables has reduced the differences between the predictions and the training data. In order to further improve the accuracy of the Neural Network predictions, a new approach is proposed that includes optimization of the activation function(s) used in the network’s neurons. In this approach, third-order Bezier Curves are used to define the activation function. The optimizer adjusts the control points for these curves to adapt the activation function(s) to the specific problem under study. Concurrently, optimization of the weighting values is being performed. A Genetic Algorithm optimizer is used to determine the superior Bezier Curve control point locations. The resulting Neural Networks demonstrate superior performance, measured by the total accuracy of the predictions, over those using traditional (i.e. non-optimized) activation functions, with error reductions from 23%-76% for three test cases.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 it