Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

IBM Watson

An Overview what is IBM WATSON and how one can work with it.

  • Login to see the comments

IBM Watson

  2. 2. Topic  What is IBM WATSON?  Watson – A Workload Optimized System  About it & Why it is created..  Architecture & process  Achievement  How we can use Watson!  Prons & Cons  References
  3. 3. What is IBM WATSON?  Watson is a customized computer system designed by IBM researchers to deliver a single, precise answer to a question processed in natural language.  Watson is a question Answering Computing System that IBM built to apply advanced NLP, information retrieval, knowledge representation, automated reasoning & machine learning technologies to be the field of open domain question answering  In Simple terms, we can say that the Watson is a super computer which is used to give answer after processing the question asked or deliver in the Human Language or Natural Language
  4. 4. Watson – A Workload Optimized System  90 x IBM Power 750 servers  2880 POWER7 cores  POWER7 3.55 GHz chip  500 GB per sec on-chip bandwidth  10 Gb Ethernet network  15 Terabyates of memory  20 Terabytes of disk, clustered  Can operate at 80 Teraflops  Runs IBM DeepQA software  Scales out with and searches vast amounts of unstructured information with UIMA & Hadoop open source components  Linux provides a scalable, open platform, optimized to exploit POWER7 performance  10 racks include servers, networking, shared disk system, cluster controllers
  5. 5. About it & Why it is created..  Project started in 2007, lead David Ferrucci  Initial goal: create a system able to process natural language & extract knowledge faster than any other computer or human  Jeopardy! was chosen because it’s a huge challenge for a computer to find the questions to such “human” answers under time pressure  Watson weighs the probability of his answer being right – doesn’t ring the buzzer if he’s not confident enough
  6. 6. Architecture
  7. 7. Achievement
  8. 8. How we can use Watson!  Answer Retrieval  News Intelligence  Social Customer Care  Text Message Chatbot  Voice of the Customer  Gallery
  9. 9. Prons & Cons PRONS  Parse textual data really well.  Features for analyzing the textual data.  No Skill Required To work with Watson. Cons  Not answers to the questions whose answers are not known  Only Answer when 100% sure.
  10. 10. References    
  11. 11. Thank you BY Harshdeep Singh