Unsupervised Feature Learning of Continuous DBN Based on Improved Dropout
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
This is the source code of the experiments in the paper Unsupervised Feature Learning of Continuous DBN Based on Improved Dropout Abstract：A continuous deep belief network (cDBN) with two hidden layers is proposed in this paper, focusing on the problem of weak feature learning ability when dealing with continuous data. In cDBN, the input data are trained in an unsupervised way by using a continuous version of transfer functions; the contrastive divergence is designed in the hidden layer training process to increase the convergence speed. An improved dropout strategy is then implemented in unsupervised training to realize features learning by decooperating between the units, and then, the network is fine-tuned using a back-propagation algorithm. In addition, hyperparameters are analyzed through stability analysis to ensure the network can find the optimal. Finally, the experiments on Lorenz chaos series, CATS benchmark and CO2 forecasting show that cDBN has the advantages of higher accuracy, a simpler structure and faster convergence speeds than other methods.
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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.006 | 0.006 |
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