Academic Journal
Automatic Implementation of Neural Networks Through Reaction Networks—Part II: Error Analysis
| Τίτλος: | Automatic Implementation of Neural Networks Through Reaction Networks—Part II: Error Analysis |
|---|---|
| Συγγραφείς: | Yuzhen Fan, Xiaoyu Zhang, Chuanhou Gao, Denis Dochain |
| Πηγή: | IEEE Transactions on Automatic Control. 70:6372-6387 |
| Publication Status: | Preprint |
| Στοιχεία εκδότη: | Institute of Electrical and Electronics Engineers (IEEE), 2025. |
| Έτος έκδοσης: | 2025 |
| Θεματικοί όροι: | Mathematics - Dynamical Systems |
| Περιγραφή: | This paired article aims to develop an automated and programmable biochemical fully connected neural network (BFCNN) with solid theoretical support. In Part I, a concrete design for BFCNN is presented, along with the validation of the effectiveness and exponential convergence of computational modules. In this article, we establish the framework for specifying the realization errors by monitoring the errors generated from approaching equilibrium points in individual modules, as well as their vertical propagation from upstream modules and horizontal accumulation from previous iterations. Ultimately, we derive the general error upper bound formula for any iteration and illustrate its exponential convergence order with respect to the phase length of the utilized chemical oscillator. The numerical experiments, based on the classification examples, reveal the tendency of total errors related to both the phase length and iteration number. |
| Τύπος εγγράφου: | Article |
| ISSN: | 2334-3303 0018-9286 |
| DOI: | 10.1109/tac.2025.3574364 |
| Σύνδεσμος πρόσβασης: | http://arxiv.org/abs/2401.07077 |
| Rights: | IEEE Copyright |
| Αριθμός Καταχώρησης: | edsair.doi.dedup.....8ff80f935814ee57298c4a23e95721db |
| Βάση Δεδομένων: | OpenAIRE |
| ISSN: | 23343303 00189286 |
|---|---|
| DOI: | 10.1109/tac.2025.3574364 |