Methods, architecture, and apparatus for implementing machine intelligence and hierarchical memory systems

Abstract

Sophisticated memory systems and intelligent machines may be constructed by creating an active memory system with a hierarchical architecture. Specifically, a system may comprise a plurality of individual cortical processing units arranged into a hierarchical structure. Each individual cortical processing unit receives a sequence of patterns as input. Each cortical processing unit processes the received input sequence of patterns using a memory containing previously encountered sequences with structure and outputs another pattern. As several input sequences are processed by a cortical processing unit, it will therefore generate a sequence of patterns on its output. The sequence of patterns on its output may be passed as an input to one or more cortical processing units in next higher layer of the hierarchy. A lowest layer of cortical processing units may receive sensory input from the outside world. The sensory input also comprises a sequence of patterns.

Description

FIELD OF THE INVENTION [0001] The present invention relates to the field of memory systems and machine intelligence. In particular the present invention discloses methods, apparatuses, and architecture for implementing memory systems that exhibit machine intelligence. BACKGROUND OF THE INVENTION [0002] The field of Artificial Intelligence (AI) has existed for over fifty years. Many useful programs have been created from artificial intelligence research such as expert systems, skilled game playing programs, and neural network based pattern matching systems. Many of the programs can accomplish feats that no human could possibly match due to the significant computational power of modern computer systems. However, no computer program has ever shown the type of understanding exhibited by the brain of even a young child. [0003] There have been two main schools of artificial intelligence research: classic artificial intelligence research and neural network research. These two main schools ...

AI Technical Summary

Benefits of technology

The present invention proposes a system for creating intelligent machines and memory systems with a hierarchical architecture. The system includes multiple cortical processing units that receive patterns and process them to generate new patterns. The higher layers of the hierarchy receive the output of the lower layers and use it to recognize and predict the next patterns in the input. The system can adjust its model of the world by storing new patterns to resolve errors. The technical effects of this invention include improved pattern recognition, prediction, and error resolution.

Problems solved by technology

However, no computer program has ever shown the type of understanding exhibited by the brain of even a young child.

However, these programs generally have no ability to learn.

These programs can only handle the single problem that was addressed.

Nor can such artificial intelligence programs generalize upon the knowledge incorporated into such programs in order to address completely novel input data.

Neural networks have been proven to be useful in some limited applications.

Although there have been some limited successes with neural networks, most neural network systems are relatively primitive.

Although neural network systems are able to ‘learn’ in a very simple sense and exhibit a limited ability to generalize, there is clearly no real understanding of the world.

The classic artificial intelligence approach has probably failed since we do not fully understand the essence of intelligence.

The neural network approach has provided very limited results since neural networks generally emulate only relatively few interconnected neurons and does so in a manner that ignores most of the complex anatomy of the brain.

Since current estimates postulate that the neocortex of the human brain contains approximately thirty billion neurons, such simple neural networks will never provide the real intelligence exhibited by the human brain.

Images