08-16-2017, 09:01 PM
[attachment=3639]
Presented By:
AARTI SHARMA
SHREYANS KOTHARI
II BE V SEM
NEURAL NETWORK
BRAIN KE BARABAR
WHAT IS NEURAL NETWORK?
A HIGHLY INTERCONNECTED NETWORK OF INFORMATION PROCESSING ELEMETS THAT MIMICS THE HUMAN BRAIN IN CONNECTIVITY & FUNCTIONALITY
WHERE CAN NEURAL NETWORK SYSTEMS HELP?
WHERE WE CAN T FORMULATE AN ALGORITHMIC SOLUTION.
WHERE WE CAN GET LOTS OF EXAMPLES.
WHERE WE NEED TO PICK OUT THE STRUCTURE FROM EXISTING DATA.
NEURAL NETWORK ADDRESS PROBLEMS:
PATTERN RECOGNISATION
HANDWRITTEN CHARACTER RECOGNISATION
SPEECH RECOGNISATION
FINANCIAL & ECONOMIC MODELING
NEXT GENERATION COMPUTING MODEL
CLASSIFICATION:
BIOLOGICAL
NEURAL NETWORK
BRAIN IS MOST FAMILIAR EXAMPLE .
APPROX 100 BILLION NERVE CELLS IN IT.
NEURONS CONNECTED TO 10,000 TO 2,00,000 OF OTHER NEURONS.
ARTIFICIAL
NEURAL NETWORK
INPUT LAYER
HIDDEN LAYER
OUTPUT LAYER
BASIC ELEMENTS OF NEURONAL MODEL
A SET OF SYNAPSES OR CONNECTING LINKS.
AN ADDER FOR SUMMING THE INPUTS.
AN ACTIVATION FUNCTION.
TRAINING SETS
NEURAL NETWORK ARE BEING USED IN:
INVESTMENT ANALYSIS.
SIGNATURE ANALYSIS.
PROCESS CONTROL.
MONITERING
PEN PC S
SPEECH & VISION RECOGNISATION
WHITE GOODS & TOYS
ADVANTAGES
NON-LINEARITY
INPUT-OUTPUT MAPPING
ADAPTIVITY
EVEDENTIAL RESPONSE
CONTEXTUAL INFORMATION
FAULT TOLERANCE
VLSI IMPLEMENTABILITY
UNIFORMITY OF ANALYSIS & DESIGN
NEUROBIOLOGICAL ANALOGY
CONCLUSION
Today, a solid basis of theory and applications is being formed and the field has begun to flourish. For a growing list of applications, the neural architecture will provide either an alternative or a complement to these other techniques.
REFRENCES
NEURAL NETWORKS
- SIMON HAYKIN
ENCARTA ENCYCLOPEDIA
GOOGLE SEARCH ENGINE
ANY QUERIES ??
THANK YOU