The shallowest transparent and interpretable deep neural network for image recognition
Bibliographic record
Abstract
Trusting the decisions of deep learning models requires transparency of their reasoning process, especially for high-risk decisions. In this paper, a fully transparent deep learning model (Shallow-ProtoPNet) is introduced. This model consists of a transparent prototype layer, followed by an indispensable fully connected layer that connects prototypes and logits, whereas usually, interpretable models are not fully transparent because they use some black-box part as their baseline. This is the difference between Shallow-ProtoPNet and prototypical part network (ProtoPNet), the proposed Shallow-ProtoPNet does not use any black box part as a baseline, whereas ProtoPNet uses convolutional layers of black-box models as the baseline. On the dataset of X-ray images, the performance of the model is comparable to the other interpretable models that are not completely transparent. Since Shallow-ProtoPNet has only one (transparent) convolutional layer and a fully connected layer, it is the shallowest transparent deep neural network with only two layers between the input and output layers. Therefore, the size of our model is much smaller than that of its counterparts, making it suitable for use in embedded systems.
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 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 | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, 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".