Two progressive improvements of Deep Learning Neural Network based on Morlet Wavelet Transforms and Long Short-Term Memory
Bibliographic record
Abstract
Convolutional neural network (CNN) is famous deep learning method, which is good at classification, prediction etc. Problems of CNN are as follows: the accuracy, precision, recall, f1 value, epoch of training etc. of CNN cannot satisfy the requirements of applications with high performance. Main work is as follows: Firstly, Morlet Wavelet- based Convolutional Neural Network (MorletWCNN) is proposed. Rectified Linear Unit (ReLU) functions in two layers (the second convolutional layer and the second fully connected layer) of CNN are replaced by wavelet transform functions. Secondly , Morlet Wavelet- based Convolutional Neural Network- Long Short-Term Memory (MorletWCNN-LSTM) is proposed. The first layer of fully connected layers of MorletWCNN is replaced by a Long Short-Term Memory layer. Thirdly, CNN, MorletWCNN and MorletWCNN-LSTM are compared based on two different datasets (Canadian Institute for Advanced Research-10 and Canadian Institute for Advanced Research-100). The effects are as follows: Firstly, the performance is improved such as the accuracy is improved by 0.0237, the precision is improved by 0.0238, the recall is improved by 0.0239, and the F1 score is improved by 0.0238. Secondly, the efficiency of algorithm is improved such as the training epochs are reduced by 18.90%.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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".