Multi-Submodel Soft-Switch ANN Framework for FET Modeling With Enhanced Convergence
Bibliographic record
Abstract
Artificial neural networks (ANNs) have been widely used in transistor modeling, but standard ANN models often suffer from convergence issues in large-signal simulation. This article investigates the root causes of such issues and identifies key problems in low voltages and ANN extrapolated regions, including nonphysical current behavior and discontinuous derivatives. To address these issues, a multi-submodel ANN framework is developed. For drain current modeling, three empirical models for low <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$V_{\text {gs}}$</tex-math> </inline-formula>, low <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$V_{\text {ds}}$</tex-math> </inline-formula>, and extrapolation regions are proposed. For gate current modeling, an information-based partition method is proposed, where ANN learning is applied only to high-information regions. A soft-switching technique is developed to ensure smooth transitions between submodels without sharp jumps or slope mismatch. The proposed modeling framework is also extended to handle temperature variation through a temperature mapping technique. It maintains modeling accuracy across a wide temperature range. Compared with standard ANN models, the proposed approach improves accuracy, physical consistency, and convergence in dc, small-signal, and large-signal tests. In particular, it remains accurate and reliable in large-signal simulations where standard ANN models do not converge.
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 | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| 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".