Why the study?
Intelligent machines lack the ability of animals to dynamically adapt intentions, attention, and actions to rich, unpredictable environments through biological mechanisms like cellular neuromodulation.
A novel deep neural network architecture inspired by cellular neuromodulation improves the adaptation of artificial systems in meta-reinforcement learning contexts.
Answers are grounded in this paper and cite their sources.
Neuromodulation principles may enable context-adaptive AI; leaves open whether they can be translated into robust machine implementations.
Animals excel at adapting their intentions, attention, and actions to the environment, making them remarkably efficient at interacting with a rich, unpredictable and ever-changing external world, a property that intelligent machines currently lack. Such an adaptation property relies heavily on cellular neuromodulation, the biological mechanism that dynamically controls intrinsic properties of neurons and their response to external stimuli in a context-dependent manner. In this paper, we take inspiration from cellular neuromodulation to construct a new deep neural network architecture that is specifically designed to learn adaptive behaviours. The network adaptation capabilities are tested on navigation benchmarks in a meta-reinforcement learning context and compared with state-of-the-art approaches. Results show that neuromodulation is capable of adapting an agent to different tasks and that neuromodulation-based approaches provide a promising way of improving adaptation of artificial systems.
No takes yet. Share an insight, caveat, or question.
Vecoven et al. (2020) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: