Knowledge Binary Information Fragment Encoding for AI System Memories

摘要

Memories involve the acquisition, categorization, classification and storage of information. The purpose of memory is to provide the ability to recall information and knowledge as well as events. We base our current understanding of the world around us on what we have previously learned, and chosen to store. Everything that we do in the present relies on memories of what has happened, or what has been learned in the past, unless new memories must be created for a new experience/ information. Without our memories, we would not be able to go through day-to-day living, using abstract thought and performing the most basic functions. Without memories we wouldn't be able to drive a car, brush our teeth, or perform any of the things we do "without thinking about them." Through our conceptual recollection of the past we are able to communicate with other people. However, the human brain does not store files in neat folders or in relational databases, but instead stores information as fragments that are used to construct memories when needed. Hence, we propose a binary information fragment encoding system for use in artificial intelligence systems that can be utilized to create a combined sensory perceptive, short-term, and long-term memory system similar to how the human brain dynamically stores and recalls (reconstructs) memories.