Convolutional Neural Networks: Estimating Relations in the Ising Model on Overfitting
Bibliographic record
Abstract
A CNN (Convolutional Neural Network) is one of actively researched and broadly applied deep machine learning methods. A CNN is composed of a feed-forward neural network that takes in images as inputs, and outputs a probability value associated to a class that best describes the image. As well, it is constructed of multiple layers, which include convolutional, max-pooling and fully connected layers. However, the training set has a large influence on the accuracy of a network, and hence it is paramount to create a network architecture that prevents overfitting (when a trained model cannot differentiate newly input data from its test data) and underfitting (the inability of a model to find relationships among inputs). This paper addresses the above deficiencies by comparing the statistics of CNN image recognition algorithms to the Ising model. The Ising model consists of magnetic dipole moments that can be in one of two states: +1 or -1. Using a two-dimensional square-lattice array once a training set of such data is complete, we determine the impact that network parameters, specifically learning rate and regularization rate, have on the adaptability of convolutional neural networks for image classification. Our results not only contribute to a better theoretical understanding of a CNN, but also provide concrete guidance on preventing model overfitting and underfitting when a CNN is applied for image recognition.
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 | 0.007 | 0.040 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.001 | 0.004 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.002 | 0.003 |
| 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".