Loading presentation...

Present Remotely

Send the link below via email or IM

Copy

Present to your audience

Start remote presentation

  • Invited audience members will follow you as you navigate and present
  • People invited to a presentation do not need a Prezi account
  • This link expires 10 minutes after you close the presentation
  • A maximum of 30 users can follow your presentation
  • Learn more about this feature in our knowledge base article

Do you really want to delete this prezi?

Neither you, nor the coeditors you shared it with will be able to recover it again.

DeleteCancel

Make your likes visible on Facebook?

Connect your Facebook account to Prezi and let your likes appear on your timeline.
You can change this under Settings & Account at any time.

No, thanks

Neural Network

Presentation One
by

Devesh Agrawal

on 23 January 2013

Comments (0)

Please log in to add your comment.

Report abuse

Transcript of Neural Network

Neural Network ENGG*4430: Neuro-Fuzzy and Soft Computing Systems CONCLUSION Optical Character Recognition (OCR)

Intelligent Character Recognition (ICR)

Natural Handwriting Recognition (NHR) Character Recognition... WHY? We use neural network!

So... Artificial Neural Network? How do we do it? Design Approach Definitely NOT 100% reliable



I get confused all the time What is a neural network?

What is an artificial neural network? A computer thing that can make decisions... CYBORG? First Thing First....
Let see if a computer can read We want a computer to read, after going through a "thinking" process.... remember CYBORG! A graphical representation of ANN Step 1: Step 2: Step 3: Use heuristics
Compare with reference images
Clustering Algorithms, etc Why not we go with what humans do??? What's up with the whole neuron thing??? We must Weight the neurons... why? P vs B PIC TEXT HANDWRITTEN Handwritten OCR ICR NHR Training the Neural Network Why would I do that? How would I do that? Back-propagation To put it simply l 1 I CYBORG MATERIAL References THANKS QUESTIONS? Neuro Dimension: http://www.nd.com/neurosolutions/products/ns/whatisNN.html Neural Networks for OCR (Cambridge Geek Night talk)by Zarkonen:
http://www.slideshare.net/Zarkonnen/neural-networks-for-ocr Free Student Projects:
http://www.freestudentprojects.com/java-projects/hand-written-pattern-recognition-system/ I do not own any of the images that are used in the presentation Presenter : Devesh Agrawal
Full transcript