Designing Ecosystems of Intelligence from First Principles
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2022
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913191933509632 |
|---|---|
| author | Friston, Karl J Ramstead, Maxwell J D Kiefer, Alex B Tschantz, Alexander Buckley, Christopher L Albarracin, Mahault Pitliya, Riddhi J Heins, Conor Klein, Brennan Millidge, Beren Sakthivadivel, Dalton A R Smithe, Toby St Clere Koudahl, Magnus Tremblay, Safae Essafi Petersen, Capm Fung, Kaiser Fox, Jason G Swanson, Steven Mapes, Dan René, Gabriel |
| author_facet | Friston, Karl J Ramstead, Maxwell J D Kiefer, Alex B Tschantz, Alexander Buckley, Christopher L Albarracin, Mahault Pitliya, Riddhi J Heins, Conor Klein, Brennan Millidge, Beren Sakthivadivel, Dalton A R Smithe, Toby St Clere Koudahl, Magnus Tremblay, Safae Essafi Petersen, Capm Fung, Kaiser Fox, Jason G Swanson, Steven Mapes, Dan René, Gabriel |
| contents | This white paper lays out a vision of research and development in the field of artificial intelligence for the next decade (and beyond). Its denouement is a cyber-physical ecosystem of natural and synthetic sense-making, in which humans are integral participants -- what we call ''shared intelligence''. This vision is premised on active inference, a formulation of adaptive behavior that can be read as a physics of intelligence, and which inherits from the physics of self-organization. In this context, we understand intelligence as the capacity to accumulate evidence for a generative model of one's sensed world -- also known as self-evidencing. Formally, this corresponds to maximizing (Bayesian) model evidence, via belief updating over several scales: i.e., inference, learning, and model selection. Operationally, this self-evidencing can be realized via (variational) message passing or belief propagation on a factor graph. Crucially, active inference foregrounds an existential imperative of intelligent systems; namely, curiosity or the resolution of uncertainty. This same imperative underwrites belief sharing in ensembles of agents, in which certain aspects (i.e., factors) of each agent's generative world model provide a common ground or frame of reference. Active inference plays a foundational role in this ecology of belief sharing -- leading to a formal account of collective intelligence that rests on shared narratives and goals. We also consider the kinds of communication protocols that must be developed to enable such an ecosystem of intelligences and motivate the development of a shared hyper-spatial modeling language and transaction protocol, as a first -- and key -- step towards such an ecology. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2212_01354 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Designing Ecosystems of Intelligence from First Principles Friston, Karl J Ramstead, Maxwell J D Kiefer, Alex B Tschantz, Alexander Buckley, Christopher L Albarracin, Mahault Pitliya, Riddhi J Heins, Conor Klein, Brennan Millidge, Beren Sakthivadivel, Dalton A R Smithe, Toby St Clere Koudahl, Magnus Tremblay, Safae Essafi Petersen, Capm Fung, Kaiser Fox, Jason G Swanson, Steven Mapes, Dan René, Gabriel Artificial Intelligence Multiagent Systems Adaptation and Self-Organizing Systems This white paper lays out a vision of research and development in the field of artificial intelligence for the next decade (and beyond). Its denouement is a cyber-physical ecosystem of natural and synthetic sense-making, in which humans are integral participants -- what we call ''shared intelligence''. This vision is premised on active inference, a formulation of adaptive behavior that can be read as a physics of intelligence, and which inherits from the physics of self-organization. In this context, we understand intelligence as the capacity to accumulate evidence for a generative model of one's sensed world -- also known as self-evidencing. Formally, this corresponds to maximizing (Bayesian) model evidence, via belief updating over several scales: i.e., inference, learning, and model selection. Operationally, this self-evidencing can be realized via (variational) message passing or belief propagation on a factor graph. Crucially, active inference foregrounds an existential imperative of intelligent systems; namely, curiosity or the resolution of uncertainty. This same imperative underwrites belief sharing in ensembles of agents, in which certain aspects (i.e., factors) of each agent's generative world model provide a common ground or frame of reference. Active inference plays a foundational role in this ecology of belief sharing -- leading to a formal account of collective intelligence that rests on shared narratives and goals. We also consider the kinds of communication protocols that must be developed to enable such an ecosystem of intelligences and motivate the development of a shared hyper-spatial modeling language and transaction protocol, as a first -- and key -- step towards such an ecology. |
| title | Designing Ecosystems of Intelligence from First Principles |
| topic | Artificial Intelligence Multiagent Systems Adaptation and Self-Organizing Systems |
| url | https://arxiv.org/abs/2212.01354 |