1. Associative Pattern Memory (APM) Larry Werth July 14, 2007

2. Introduction and Background of APM
Human Associative Pattern Memory
Computer Implemented APM
Basis for Two Successful Startup Companies
Six Patents Granted and Others Pending
Successful Implementation of NKS

3. Objective of My Presentation
Describe the APM Concept & Implementation
Describe its Advantages / Features
Identify Types of Applications
Describe its Current Status and Future Goals

4. Origin of Concept Randomly Connected Neural Network Models
States Sequence Terminates in a Cycle
Randomly Map Each State to an Input Pattern
Sampled Pattern Value & Current State Determine Next State
The Ultimate Cycle Represents the Input Pattern
Cycles Form the Basis of the APM

5. Cycle Properties Randomly Connected DFA’s
Expected# Expected# Expected# Fraction
Terminal Number Transition Terminal
Total States (N) States(S) Cycles(C) States(T) States(F) 1,
10,
100,
1,000,000 1,
10,000,000 3,
100,000, ,
1,000,000,000 39,

6. Conceptual Implementation of APM
Train Pattern
(Write to Cycle Addresses)
Input Pattern
Array
State Array
Pattern Address
Current
State Address
Next State Address
Response Array
Next State Array (Value = 0)
Respond to Pattern
(Read From Cycle Addresses)
Pattern Value
Next State Array (Value = 1)
State Array: Filled with Random Pattern Addresses
Next State Arrays : Filled with Random State Addresses
Response Array: Assigned Responses to Patterns

7. Solution to Multiple Cycles
Introduce a Refractory Period
A State Can Not Occur Again Until After a Specified Number of Steps
Establishes a Minimum Cycle Length
Assures One Cycle Per Input Pattern Independent of Initial State
Input Pattern is Represented By a Single Sequence of Random Addresses in Memory

8. Minimum Cycle Length Example
Number of States: 1,000,000
Minimum Cycle Length: 3,700
Probability of a Second Cycle of 3,700 in Length: 1 in 1,000,000
Based on the probability of not picking one of 3700 in 1,000,000 after 3700 tries.

9. Response/Recognition Capacity
During Training Desired Responses are Written to Cycle Addresses in Response Memory
Problem: Response Memory Fills UP Quickly
Any Cycle Address has Memory of Previous Input Sample Values
Do Not Need to Use All Cycle Addresses
Solution: Vertical Sensors

10. Vertical Sensor Cycle Detection
Upper Memory Plane forms New Input Pattern Based on Sensor Status
Vertical Sensors Detect Presence Absence of Cycle
State Addresses Plane With Cycle

11. Vertical Sensor Implementation
Number of States: 1,000,000
Minimum Cycle Length: 3,700
One of 270 Addresses are in Cycles
Vertical Sensor Field Size: 135
Probability Field Contains Cycle Address: .5
Vertical Sensor Determines Bit Status of Hash Values that Addresses Response Memory

12. Fuzzy Hash Similar Input Patterns Produce Similar Cycles
Similar Input Patterns Generate the same or Similar Hash Codes
Multiple Independent Hash Codes are Generated By One Cycle (One Input Pattern)
A Voting Mode For Response Identification Contributes to Fuzzy Recognition

13. Advantages of Using Cycles
Creates a Fuzzy Hash
Simple and Fast Implementation
Common Language for Different Pattern Types
Spatial and Temporal Integration to Form New Higher Level Input Patterns
Automatic Segmentation of Time Varying Patterns

14. Applications
Actual Applications: Hand Printed Character Recognition, Machine Vision, Video Compression, Financial Pattern Forecasting
Signal Processing – Vector Quantization
Video Surveillance – Smart Cameras
Video Object Tracking
Stereo Vision

15. Current Status and Objectives
Software Library Written in C/C++
Objective: General Purpose Tool for Pattern Recognition Development
Looking for a Business Partner
Software Will be Available on Our Web Site