Designing Ecosystems of Intelligence from First Principles

by   Karl J. Friston, et al.

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 participantsx2014what 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 worldx2014also 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 sharingx2014leading 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 firstx2014and keyx2014step towards such an ecology.


Demystifying active inference

Active inference is a first (Bayesian) principles account of how autonom...

Realising Active Inference in Variational Message Passing: the Outcome-blind Certainty Seeker

Active inference is a state-of-the-art framework in neuroscience that of...

Realising Synthetic Active Inference Agents, Part II: Variational Message Updates

The Free Energy Principle (FEP) describes (biological) agents as minimis...

Accuracy-Memory Tradeoffs and Phase Transitions in Belief Propagation

The analysis of Belief Propagation and other algorithms for the reconst...

Modular Belief Updates and Confusion about Measures of Certainty in Artificial Intelligence Research

Over the last decade, there has been growing interest in the use or meas...

AIDA: An Active Inference-based Design Agent for Audio Processing Algorithms

In this paper we present AIDA, which is an active inference-based agent ...

Please sign up or login with your details

Forgot password? Click here to reset