Thermodynamic Neural Network
A thermodynamically motivated neural network model is described that self-organizes to transport charge associated with internal and external potentials while in contact with a thermal reservoir. The model integrates techniques for rapid, large-scale, reversible, conservative equilibration of node states and slow, small-scale, irreversible, dissipative adaptation of the edge states as a means to create multiscale order. All interactions in the network are local and the network structures can be generic and recurrent. Isolated networks show multiscale dynamics, and externally driven networks evolve to efficiently connect external positive and negative potentials. The model integrates concepts of conservation, potentiation, fluctuation, dissipation, adaptation, equilibration and causation to illustrate the thermodynamic evolution of organization in open systems. A key conclusion of the work is that the transport and dissipation of conserved physical quantities drives the self-organization of open thermodynamic systems.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2020 |
|---|---|
| Erschienen: |
2020 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:22 |
|---|---|
| Enthalten in: |
Entropy (Basel, Switzerland) - 22(2020), 3 vom: 25. Feb. |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Hylton, Todd [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Causal learning |
|---|
| Anmerkungen: |
Date Revised 10.12.2020 published: Electronic Citation Status PubMed-not-MEDLINE |
|---|
| doi: |
10.3390/e22030256 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM318518392 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM318518392 | ||
| 003 | DE-627 | ||
| 005 | 20231225165522.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231225s2020 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.3390/e22030256 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1061.xml |
| 035 | |a (DE-627)NLM318518392 | ||
| 035 | |a (NLM)33286033 | ||
| 035 | |a (PII)E256 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Hylton, Todd |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Thermodynamic Neural Network |
| 264 | 1 | |c 2020 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Revised 10.12.2020 | ||
| 500 | |a published: Electronic | ||
| 500 | |a Citation Status PubMed-not-MEDLINE | ||
| 520 | |a A thermodynamically motivated neural network model is described that self-organizes to transport charge associated with internal and external potentials while in contact with a thermal reservoir. The model integrates techniques for rapid, large-scale, reversible, conservative equilibration of node states and slow, small-scale, irreversible, dissipative adaptation of the edge states as a means to create multiscale order. All interactions in the network are local and the network structures can be generic and recurrent. Isolated networks show multiscale dynamics, and externally driven networks evolve to efficiently connect external positive and negative potentials. The model integrates concepts of conservation, potentiation, fluctuation, dissipation, adaptation, equilibration and causation to illustrate the thermodynamic evolution of organization in open systems. A key conclusion of the work is that the transport and dissipation of conserved physical quantities drives the self-organization of open thermodynamic systems | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a causal learning | |
| 650 | 4 | |a dissipative adaptation | |
| 650 | 4 | |a multiscale complex systems | |
| 650 | 4 | |a neural networks | |
| 650 | 4 | |a open thermodynamic systems | |
| 650 | 4 | |a self-organization | |
| 650 | 4 | |a thermodynamic evolution | |
| 773 | 0 | 8 | |i Enthalten in |t Entropy (Basel, Switzerland) |d 2008 |g 22(2020), 3 vom: 25. Feb. |w (DE-627)NLM191572098 |x 1099-4300 |7 nnns |
| 773 | 1 | 8 | |g volume:22 |g year:2020 |g number:3 |g day:25 |g month:02 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.3390/e22030256 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 22 |j 2020 |e 3 |b 25 |c 02 | ||