Context and event-based cognitive memory constructs for embodied intelligence machines

Abstract

Any algorithm that needs to "understand" information to be capable of taking "intelligent" decisions, needs to access a lifetime of memories and experience the world as an embodied consciousness. This paper emphasizes these concepts and proposes a few fundamental constructs that provide algorithms with the capability to understand the human world, build larger sets of cooperative machines and perform causal inferences without requiring human intervention.<br>

An In-Memory Physics Environment as a World Model for Robot Motion Planning

“…These are a crucial task that simplistic algorithms like ANN cannot perform effectively, due to being dependent on neural weights, rather than depending on a database containing a lifetime of acquired information. A fullfledged event-based memory for intelligent machines however [29], could augment or even replace the need for utilizing physics simulations to create an in-memory world-model.…”