Cellular Automata Machine For Pattern Recognition Pradipta Maji 1 Niloy Ganguly 2 Sourav Saha 1 Anup K Roy 1 P Pal Chaudhuri 1 1 Department of Computer.

Slides:



Advertisements
Similar presentations
High Performance Associative Neural Networks: Overview and Library High Performance Associative Neural Networks: Overview and Library Presented at AI06,
Advertisements

Bioinspired Computing Lecture 16
MEMORY popo.
Cellular Automata (CA) - Theory & Application
Embedded Algorithm in Hardware: A Scalable Compact Genetic Algorithm Prabhas Chongstitvatana Chulalongkorn University.
Sequential Circuits1 DIGITAL LOGIC DESIGN by Dr. Fenghui Yao Tennessee State University Department of Computer Science Nashville, TN.
School of Cybernetics, School of Systems Engineering, University of Reading Presentation Skills Workshop March 22, ‘11 Diagnosis of Breast Cancer by Modular.
Submission May, 2000 Doc: IEEE / 086 Steven Gray, Nokia Slide Brief Overview of Information Theory and Channel Coding Steven D. Gray 1.
1 Neural networks 3. 2 Hopfield network (HN) model A Hopfield network is a form of recurrent artificial neural network invented by John Hopfield in 1982.
Nitin Yogi and Vishwani D. Agrawal Auburn University Auburn, AL 36849
11/17/05ELEC / Lecture 201 ELEC / (Fall 2005) Special Topics in Electrical Engineering Low-Power Design of Electronic Circuits.
Department of Computer Engineering University of California at Santa Cruz Networking Systems (1) Hai Tao.
Computational Modelling of Road Traffic SS Computational Project by David Clarke Supervisor Mauro Ferreira - Merging Two Roads into One As economies grow.
Basic Models in Neuroscience Oren Shriki 2010 Associative Memory 1.
1 Regular expression matching with input compression : a hardware design for use within network intrusion detection systems Department of Computer Science.
Comparison of LFSR and CA for BIST
DIGITAL ELECTRONICS CIRCUIT P.K.NAYAK P.K.NAYAK ASST. PROFESSOR SYNERGY INSTITUTE OF ENGINEERING & TECHNOLOGY.
1 Image Processing(IP) 1. Introduction 2. Digital Image Fundamentals 3. Image Enhancement in the spatial Domain 4. Image Enhancement in the Frequency Domain.
296.3Page :Algorithms in the Real World Convolutional Coding & Viterbi Decoding.
Nawaf M Albadia Introduction. Components. Behavior & Characteristics. Classes & Rules. Grid Dimensions. Evolving Cellular Automata using Genetic.
Generating Random Numbers in Hardware. Two types of random numbers used in computing: --”true” random numbers: ++generated from a physical source (e.g.,
Department of Information Technology Indian Institute of Information Technology and Management Gwalior AASF hIQ 1 st Nov ‘09 Department of Information.
Theory and Applications of GF(2 p ) Cellular Automata P. Pal Chaudhuri Department of CST Bengal Engineering College (DU) Shibpur, Howrah India (LOGIC ON.
Pattern Similarity and Storage Capacity of Hopfield Network Suman K Manandhar Prof. Ramakoti Sadananda Computer Science and Information Management AIT.
Governor’s School for the Sciences Mathematics Day 13.
 The most intelligent device - “Human Brain”.  The machine that revolutionized the whole world – “computer”.  Inefficiencies of the computer has lead.
Cellular Automata Evolution : Theory and Applications in Pattern Recognition and Classification Niloy Ganguly.
Cellular Automata Based Authentication (CAA ) Monalisa Mukherjee 1 Niloy Ganguly 2 P Pal Chaudhuri 1 1 Department of Computer Science & Technology, Bengal.
Pseudo-Random Pattern Generator Design for Column ‑ Matching BIST Petr Fišer Czech Technical University Dept. of Computer Science and Engineering.
Hebbian Coincidence Learning
1 Cellular Automata and Applications Ajith Abraham Telephone Number: (918) WWW:
EKT 221/4 DIGITAL ELECTRONICS II  Registers, Micro-operations and Implementations - Part3.
CSC321: Introduction to Neural Networks and machine Learning Lecture 16: Hopfield nets and simulated annealing Geoffrey Hinton.
Trust Propagation using Cellular Automata for UbiComp 28 th May 2004 —————— Dr. David Llewellyn-Jones, Prof. Madjid Merabti, Dr. Qi Shi, Dr. Bob Askwith.
Cellular Automata based Edge Detection. Cellular Automata Definition A discrete mathematical system characterized by local interaction and an inherently.
1 KU College of Engineering Elec 204: Digital Systems Design Lecture 11 Binary Adder/Subtractor.
Activations, attractors, and associators Jaap Murre Universiteit van Amsterdam
Unifying Dynamical Systems and Complex Networks Theories ~ A Proposal of “Generative Network Automata (GNA)” ~ Unifying Dynamical Systems and Complex Networks.
Niloy Ganguly Biplab K Sikdar P Pal Chaudhuri Presented by Niloy Ganguly Indian Institute of Social Welfare and Business Management. Calcutta
Analyzing the Vulnerability of Superpeer Networks Against Attack Niloy Ganguly Department of Computer Science & Engineering Indian Institute of Technology,
PRESENTAION TOPIC : DSS Development Presented TO: Sir Ahmad Tisman Pasha Presented BY : Uzma Noreen Roll # BSIT (6 th ) Department.
Neural Networks and Machine Learning Applications CSC 563 Prof. Mohamed Batouche Computer Science Department CCIS – King Saud University Riyadh, Saudi.
Modeling Mobile-Agent-based Collaborative Processing in Sensor Networks Using Generalized Stochastic Petri Nets Hongtao Du, Hairong Qi, Gregory Peterson.
Hardware Accelerator for Combinatorial Optimization Fujian Li Advisor: Dr. Areibi.
A Biased Fault Attack on the Time Redundancy Countermeasure for AES Sikhar Patranabis, Abhishek Chakraborty, Phuong Ha Nguyen and Debdeep Mukhopadhyay.
BIST Pattern Generator inserter using Cellular Automata By Jeffrey Dwoskin Project for Testing of ULSI Circuits, Spring 2002, Rutgers University 5/15/02.
Cellular Automata Introduction  Cellular Automata originally devised in the late 1940s by Stan Ulam (a mathematician) and John von Neumann.  Originally.
Priority encoder. Overview Priority encoder- theoretic view Other implementations The chosen implementation- simulations Calculations and comparisons.
Cellular Automata Based Hamming Hash Family : Synthesis and Application CELLULAR AUTOMATA BASED HAMMING HASH FAMILY : SYNTHESIS AND APPLICATION Niloy Ganguly.
Intro to Life32. 1)Zoom to 10 That will allow you to see the grid and individual cells.
Brief Announcement : Measuring Robustness of Superpeer Topologies Niloy Ganguly Department of Computer Science & Engineering Indian Institute of Technology,
Design of a Robust Search Algorithm for P2P Networks
Designing High-Capacity Neural Networks for Storing, Retrieving and Forgetting Patterns in Real-Time Dmitry O. Gorodnichy IMMS, Cybernetics Center of Ukrainian.
November 25Asian Test Symposium 2008, Nov 24-27, Sapporo, Japan1 Sequential Circuit BIST Synthesis using Spectrum and Noise from ATPG Patterns Nitin Yogi.
July 10, th VLSI Design and Test Symposium1 BIST / Test-Decompressor Design using Combinational Test Spectrum Nitin Yogi Vishwani D. Agrawal Auburn.
Chapter 12 Case Studies Part B. Control System Design.
296.3:Algorithms in the Real World
Hiroki Sayama NECSI Summer School 2008 Week 3: Methods for the Study of Complex Systems Cellular Automata Hiroki Sayama
On Routine Evolution of Complex Cellular Automata
Ch7: Hopfield Neural Model
© The Author(s) Published by Science and Education Publishing.
ECE 553: TESTING AND TESTABLE DESIGN OF DIGITAL SYSTES
Corso su Sistemi complessi:
Recurrent Networks A recurrent network is characterized by
The Engineering of Functional Designs in the Game of Life
Testing Mechanisms for Open-ended Evolution in Reversible CA
Binary Adder/Subtractor
Von Neumann’s Automaton and Viruses
Complexity as Fitness for Evolved Cellular Automata Update Rules
Simulated Annealing & Boltzmann Machines
Presentation transcript:

Cellular Automata Machine For Pattern Recognition Pradipta Maji 1 Niloy Ganguly 2 Sourav Saha 1 Anup K Roy 1 P Pal Chaudhuri 1 1 Department of Computer Science & Technology, Bengal Engineering College ( D. U ), Howrah, West Bengal, India Department of Business Administration, Indian Institute of Social Welfare and Business Management, Calcutta, West Bengal, India

CA Research Group (BECDU) The Problem Pattern Recognition - Study how machines can learn to distinguish patterns of interest Conventional Approach - Compares input patterns with each of the stored patterns learn AB C…ZAB C…Z Bookman Old Style A Comic Sans MS CA Research Group (BECDU)

The Problem A Comic Sans MS A A B AB C…ZAB C…Z Bookman old Style Grid by Grid Comparison CA Research Group (BECDU)

The Problem A A B Grid by Grid Comparison No of Mismatch = 3 CA Research Group (BECDU)

The Problem A A B Grid by Grid Comparison No of Mismatch = 9 CA Research Group (BECDU)

The Problem Time to recognize a pattern - Proportional to the number of stored patterns ( Too costly with the increase of number of patterns stored ) Solution - Associative Memory Modeling CA Research Group (BECDU)

The Problem Time to recognize a pattern - Proportional to the number of stored patterns ( Too costly with the increase of number of patterns stored ) Solution - Associative Memory Modeling A B C CA Research Group (BECDU) Transient A A A A A A

CA Research Group (BECDU) Associative Memory Entire state space - Divided into some pivotal points. State close to pivot - Associated with that pivot. Time to recognize pattern- Independent of number of stored patterns. A B C Transient A A A A A A CA Research Group (BECDU)

Associative Memory Two Phase : Learning and Detection Time to learn is higher Driving a car Difficult to learn but once learnt it becomes natural A B C Transient A A A A A A CA Research Group (BECDU)

Associative Memory (Hopfield Net)  Densely connected Network - Problems to implement in Hardware Solution - Cellular Automata (Sparsely connected machine) - Ideally suitable for VLSI application A B C Transient A A A A A A CA Research Group (BECDU)

Cellular Automata VLSI Domain India under Prof. P Pal Chaudhuri Late 80’s - Work at Indian Institute of Technology Kharagpur Late 90’s - Work at Bengal Engineering College Deemed University, Calcutta  Book - Additive Cellular Automata Vol I, IEEE Press CA Research Group (BECDU)

Cellular Automata  A computational Model with discrete cells updated synchronously ……….. output Input Combinatio nal Logic Clock From Left Neighbor From Right Neighbor 0/1 2 - State 3- Neighborhood CA Cell CA Research Group (BECDU)

Cellular Automata Combinational Logic can be of 256 types each type is called a rule Each cell can have 256 different rules ……….. CA Research Group (BECDU) cell CA with different rules at each cell

CA Research Group (BECDU) State Transition Diagram CA Research Group (BECDU)

Generalized Multiple Attractor CA A B C Transient A A A A A A The State Space of GMACA – Models an Associative Memory P1 attractor-1 P2 atractor-2 Rule vector: CA Research Group (BECDU)

Generalized Multiple Attractor CA P1 attractor-1 P2 atractor-2 Rule vector: CA Research Group (BECDU) Pivot Points Dist =3 Dist =1  The state transition diagram breaks into disjoint attractor basin  Each attractor basin of CA should contain one and only one pattern to be learnt in its attractor cycle  The hamming distance of each state with its attractor is less than that of other attractors.

CA Research Group (BECDU) Synthesis of GMACA Reverse Engineering Technique Phase I: Random Generation of a set of directed Graph Basin Basin 2 Patterns to be learnt P1 = 0000 P2 = 1111 Number of bits of noise = 1 CA Research Group (BECDU) 1 0

Synthesis of GMACA Reverse Engineering Technique Phase II: State transition table from Graph Basin CA Research Group (BECDU)

Synthesis of GMACA Reverse Engineering Technique Phase II: State transition table from Graph CA Research Group (BECDU) Basin 2

CA Research Group (BECDU) Synthesis of GMACA Reverse Engineering Technique Phase III: GMACA rule vector from State transition table CA Research Group (BECDU) Basin 1Basin 2

CA Research Group (BECDU) Synthesis of GMACA Reverse Engineering Technique Phase III: GMACA rule vector from State transition table CA Research Group (BECDU) Basin 1Basin 2

CA Research Group (BECDU) Synthesis of GMACA Reverse Engineering Technique Phase III: GMACA rule vector from State transition table CA Research Group (BECDU) Basin 1Basin Rule 232

CA Research Group (BECDU) Synthesis of GMACA Reverse Engineering Technique Phase III: GMACA rule vector from State transition table CA Research Group (BECDU) Basin 1Basin /1? Collision

CA Research Group (BECDU) Synthesis of GMACA Reverse Engineering Technique Phase III: GMACA rule vector from State transition table CA Research Group (BECDU) 0/1? Collision Less the number of collision better the design. Design Objective : Design GMACA so that there is minimum number of collision during rule formation Simulated Annealing to attain the design

CA Research Group (BECDU) Objective Reduce Collision Increment of Cycle Length Simulated Annealing Program Mutation Technique Cycle Length = Cycle Length =

CA Research Group (BECDU) Simulated Annealing Program Increment of Cycle Length *1*0*0* 0/1? Cycle Length =

CA Research Group (BECDU) Simulated Annealing Program Increment of Cycle Length *1*0*0* 0/1? Cycle Length = 2 0 *1*0*0*

CA Research Group (BECDU) Reduction of Cycle Length Simulated Annealing Program Mutation Technique - 2 Cycle Length = Cycle Length =

CA Research Group (BECDU) Simulated Annealing Program Decrement of Cycle Length /1? *0*0*1* Cycle Length =

CA Research Group (BECDU) Simulated Annealing Program Decrement of Cycle Length *1*0*0* 0/1? *1*0*0* Cycle Length =

CA Research Group (BECDU) Memorizing Capacity Evolution Time Identification / Recognition Complexity Performance of GMACA Based Pattern Recognizer

CA Research Group (BECDU) Memorizing Capacity  Conclusion : GMACA have much higher capacity than Hopfield Net

CA Research Group (BECDU) Evolution Time

CA Research Group (BECDU) Identification / Recognition Complexity Cost of Computation for Recognition / Identification - Constant

CA Research Group (BECDU) Achievements 1.Cellular Automata - A powerful machine in designing the pattern recognition tool 2.Storage Capacity of CA - Higher than Hopfield Net 3.A clever reverse engineering technique is employed to design Cellular Automata based Associative Memory

CA Research Group (BECDU) Publications Study of Non-Linear Cellular Automata For Pattern Recognition To be published in IEEE Transaction, Man, Machine and Cybernetics, Part - B Generalized Multiple Attractor Cellular Automata(GMACA) Model for Associative Memory Niloy Ganguly, Pradipta Maji, Biplab k Sikdar and P Pal Chaudhuri To be published in International Journal for Pattern Recognition and Artificial Intelligence Error Correcting Capability of Cellular Automata Based Associative Memory, IEEE Transaction, Man, Machine and Cybernetics, Part - A

Thank you Niloy Ganguly