Post-Workshop Report on Science meets Engineering in Deep Learning,\n NeurIPS 2019, Vancouver
Bibliographic record
Abstract
Science meets Engineering in Deep Learning took place in Vancouver as part of\nthe Workshop section of NeurIPS 2019. As organizers of the workshop, we created\nthe following report in an attempt to isolate emerging topics and recurring\nthemes that have been presented throughout the event. Deep learning can still\nbe a complex mix of art and engineering despite its tremendous success in\nrecent years. The workshop aimed at gathering people across the board to\naddress seemingly contrasting challenges in the problems they are working on.\nAs part of the call for the workshop, particular attention has been given to\nthe interdependence of architecture, data, and optimization that gives rise to\nan enormous landscape of design and performance intricacies that are not\nwell-understood. This year, our goal was to emphasize the following directions\nin our community: (i) identify obstacles in the way to better models and\nalgorithms; (ii) identify the general trends from which we would like to build\nscientific and potentially theoretical understanding; and (iii) the rigorous\ndesign of scientific experiments and experimental protocols whose purpose is to\nresolve and pinpoint the origin of mysteries while ensuring reproducibility and\nrobustness of conclusions. In the event, these topics emerged and were broadly\ndiscussed, matching our expectations and paving the way for new studies in\nthese directions. While we acknowledge that the text is naturally biased as it\ncomes through our lens, here we present an attempt to do a fair job of\nhighlighting the outcome of the workshop.\n
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 | 0.000 | 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 | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.003 | 0.003 |
| Research integrity | 0.000 | 0.002 |
| 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".