Encompassing Chaos in Brain-inspired Neural Network Models for Substance Identification and Breast Cancer Detection
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
The main purpose in this work is to explore the fact that chaos, as a biological characteristic in the brain, should be used in an Artificial Neural Network (ANN) system.In fact, as long as chaos is present in brain functionalities, its properties need empirical investigations to show their potential to enhance accuracies in artificial neural network models.In this paper, we present brain-inspired neural network models applied as pattern recognition techniques first as an intelligent data processing module for an optoelectronic multi-wavelength biosensor, and second for breast cancer identification.To this purpose, the simultaneous use of three different neural network behaviors in the present work allows a performance differentiation between the pioneer classifier such as the multilayer perceptron employing the Resilient back Propagation (RProp) algorithm as a learning rule, a heteroassociative Bidirectional Associative Memory (BAM), and a Chaotic-BAM (CBAM).It is to be noted that this would be in two different multidimensional space problems.The later model is experimented on a set of different chaotic output maps before converging to the ANN model that remarkably leads to a perfect recognition for both reallife domains.Empirical exploration of chaotic properties on the memory-based models and their performances shows the ability of a specific modelisation of the whole system that totally satisfies the exigencies of a perfect pattern recognition performance.Accordingly, the experimental results revealed that, beyond chaos' biological plausibility, the perfect accuracy obtained stems from the potential of chaos in the model: (1) the model offers the ability to learn categories by developing prototype representations from exposition to a limited set of exemplars because of its interesting capacity of generalization, and (2) it can generate perfect outputs from incomplete and noisy data since chaos makes the ANN system capable of being resilient to noise.
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 | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| 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