Intriguing Properties of Randomly Weighted Networks: Generalizing While\n Learning Next to Nothing
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
Training deep neural networks results in strong learned representations that\nshow good generalization capabilities. In most cases, training involves\niterative modification of all weights inside the network via back-propagation.\nIn Extreme Learning Machines, it has been suggested to set the first layer of a\nnetwork to fixed random values instead of learning it. In this paper, we\npropose to take this approach a step further and fix almost all layers of a\ndeep convolutional neural network, allowing only a small portion of the weights\nto be learned. As our experiments show, fixing even the majority of the\nparameters of the network often results in performance which is on par with the\nperformance of learning all of them. The implications of this intriguing\nproperty of deep neural networks are discussed and we suggest ways to harness\nit to create more robust representations.\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.
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 | 0.002 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.004 | 0.005 |
| Research integrity | 0.001 | 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 it