Neural Controlled Differential Equations with Quantum Hidden Evolutions
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912160493338624 |
|---|---|
| author | Yang, Lingyi Shao, Zhen |
| author_facet | Yang, Lingyi Shao, Zhen |
| contents | We introduce a class of neural controlled differential equation inspired by quantum mechanics. Neural quantum controlled differential equations (NQDEs) model the dynamics by analogue of the Schrödinger equation. Specifically, the hidden state represents the wave function, and its collapse leads to an interpretation of the classification probability. We implement and compare the results of four variants of NQDEs on a toy spiral classification problem. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_19673 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Neural Controlled Differential Equations with Quantum Hidden Evolutions Yang, Lingyi Shao, Zhen Machine Learning We introduce a class of neural controlled differential equation inspired by quantum mechanics. Neural quantum controlled differential equations (NQDEs) model the dynamics by analogue of the Schrödinger equation. Specifically, the hidden state represents the wave function, and its collapse leads to an interpretation of the classification probability. We implement and compare the results of four variants of NQDEs on a toy spiral classification problem. |
| title | Neural Controlled Differential Equations with Quantum Hidden Evolutions |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2404.19673 |