Number of Autonomous Cognitive Agents in a Neural Network
Journal of Artificial Intelligence and Consciousness September 1, 2022 DOI: 10.1142/s2705078522500023 (opens in new tab)
Study at a glance
AI-extracted from the abstract| Characteristics | Theoretical or philosophical paper Peer reviewed |
|---|---|
| Key points | Argues that autonomous cognitive agents in a neural network are best counted using the dimensionality of the underlying space, and that propagation speed creates a dichotomy of causal and noncausal regions in which such agents are not causally bound to one another. The authors report a count of 25 autonomous agents for the human brain, with sub-system modules close to the same value, and propose this near equality may give the human brain a special uniqueness. |
Abstract
This paper considers several aspects of the relationship between size, structure, speed of propagation and the number of autonomous cognitive agents in a neural network. While memory and function generation capacities of neural networks with scale-invariant structure have been investigated extensively, the number of autonomous agents, associated with the simultaneous processing of the independent components of the data, has not received prior attention. We propose the emergence of the dichotomy of causal and noncausal regions created by the speed of propagation, in which the autonomous cognitive agents are not bound in a causal relationship with other agents. Arguments are presented for why the count of autonomous agents is best estimated with respect to the dimensionality of the underlying space. The number of autonomous agents obtained for the human brain equals 25, and it is significant that the number in the sub-system modules also turns out to be close to the same value. This number equals the number of enumerative categories of reality in at least one philosophical tradition, and this coincidence may be attributed to the capacity of consciousness to reflect on its own structure. It is possible that near equality across layers provides a special uniqueness to the human brain. We propose that the findings of this study will be useful in the design of neural-network-based AI systems that are designed to emulate human cognitive capacity.