Projection Learning vs. Correlation Learning: From Pavlov Dogs to Face Recognition
Bibliographic record
Abstract
Face recognition in video is an example of the problem which is outstandingly well performed by humans, compared to the performance of machine-built recognition systems. This phenomenon is generally attributed to the following three main factors pertaining to the way human brain processes and memorizes information, which can be succinctly labeled as 1) non-linear processing, 2) massively distributed collective decision making, and 3) synaptic plasticity. Over the last half a century, many mathematical models have been developed to simulate these factors in computer systems.This presentation formalizes the recognition process, as it is performed in brain, using one of such mathematical models, within which the projection learning appears to be a natural improvement to the correlation learning. We show that, just as the correlation learning, the projection learning can also be written in incremental form. By taking in account the past data and being non-local, this rule however provides a way to automatically emphasize more important attributes and training data over the less important ones. The presented model, while providing a simple way to incorporate the main three factors of biological memorization listed above, is very powerful. This is demonstrated by incorporating it into a face recognition system which is shown to be capable of recognizing faces in video under conditions known to be very difficult for traditional Von-Neumann-type recognition 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 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 | 0.001 | 0.002 |
| 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 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".