Activation Function Modulation in Generative Triangular Recurrent Neural Networks
Bibliographic record
Abstract
Autonomous generation of time series is challenging because the network must capture short-term features while tracking long-term time dependencies. This paper introduces the modulation of the activation function slopes of the upper-lower triangular recurrent neural networks (ULTRNNs) for dynamic variation of memory through a secondary recurrent network with its own independent states. A zigzag propagation algorithm for weight updates is proposed that accounts for the dynamic interaction of the states between the ULTRNN and the secondary network. A novel training method is proposed that distributes the eigenvalues of the closed-loop system around the unit circle in the complex z-plane to ensure that the network behaves as a nonlinear oscillator with an output that neither collapses nor saturates but continues to emulate the target. Examples encompassing the Lorenz series, Santa Fe laser data,kolampatterns, electrocardiogram (ECG) signals, stock pricing data, and smart grid data are presented to demonstrate that the proposed approach is highly effective in the generative modeling of complex periodic, chaotic, and nonstationary time series. The qualitative and quantitative performance of the ULTRNN obtained with the proposed activation-function modulation technique is comparable to that of state-of-the-art techniques including feedforward networks and generative adversarial networks, but with far fewer trainable parameters and shorter computation times.
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) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".