UNIT 2
(Artificial Intelligence &
Machine Learning)
What is machine learning ?
Traditional programming VS Machine
Learning
Some more examples of tasks that are best
solved by using a learning algorithm
Recognizing patterns:
• – Facial identities or facial expressions
• – Handwritten or spoken words
• – Medical images
• Generating patterns:
• Generating images or motion sequences
• Recognizing anomalies:
• – Unusual credit card transactions
• – Unusual patterns of sensor readings in a nuclear power plant
• Prediction:
• – Future stock prices or currency exchange rates
Other Applications of Machine Learning
Types of Machine Learning
Types of Machine Learning
Semi-Supervised
Learning
Model trained with
labelled and unlabelled
data
Issues
• Many machine learning/AI projects fail
(Gartner claims 85 %)
• Ethics, e.g., Amazon has/had
sub-par employees fired by an AI
automatically
Reasons for failure
• Asking the wrong question
• Trying to solve the wrong problem
• Not having enough data
• Not having the right data
• Having too much data
• Hiring the wrong people
• Using the wrong tools
• Not having the right model
• Not having the right yardstick
Next class
Next: Unlocking the Secrets of AI's Branches!

Unit 2 part 1 Artifical intelligence .ppt

  • 2.
  • 3.
    What is machinelearning ?
  • 4.
  • 5.
    Some more examplesof tasks that are best solved by using a learning algorithm Recognizing patterns: • – Facial identities or facial expressions • – Handwritten or spoken words • – Medical images • Generating patterns: • Generating images or motion sequences • Recognizing anomalies: • – Unusual credit card transactions • – Unusual patterns of sensor readings in a nuclear power plant • Prediction: • – Future stock prices or currency exchange rates
  • 6.
    Other Applications ofMachine Learning
  • 7.
  • 8.
    Types of MachineLearning Semi-Supervised Learning Model trained with labelled and unlabelled data
  • 9.
    Issues • Many machinelearning/AI projects fail (Gartner claims 85 %) • Ethics, e.g., Amazon has/had sub-par employees fired by an AI automatically
  • 10.
    Reasons for failure •Asking the wrong question • Trying to solve the wrong problem • Not having enough data • Not having the right data • Having too much data • Hiring the wrong people • Using the wrong tools • Not having the right model • Not having the right yardstick
  • 11.
    Next class Next: Unlockingthe Secrets of AI's Branches!