1. MACHINE
LEARNING

2. What is AI ?
Artificial Intelligence is the branch of computer science concerned with making computers behave like humans. The term was coined in 1956 by John McCarthy at the Massachusetts Institute of Technology.

3. Earlier developments in AI
Turing’s Test
Dartmouth Conference 1956
 The event which led to the birth of AI ,Organised by Marvin Minsky, John McCarthy and two senior scientists: Claude Shannon and Nathan Rochester of IBM.
“Every aspect of learning or any other feature of intelligence can be so precisely described that a machine can be made to simulate it"

4. Learning from experience
Machine Learning
A branch of artificial intelligence , concerned with the construction and study of systems that can learn from data
Programs that can automatically improve their performance through experience without explicit programming
Focuses on the development of computer programs that can teach themselves to grow and change when exposed to new data.
Learning from experience

5. How it Works?

6. The Concept of Learning in a MLS
Learning = Improving with experience at some task
Improve over task T
With respect to performance measure P
Based on experience E

8. Machine Learning Techniques
Classification : Predict class from observations.
Clustering: Group observations into “meaningful” groups.
Regression (prediction): Predict value from observations.

9. Classification Classify a document into a predefined category.
Documents can be text, images
Popular one is Naïve Bayes Classifier.
Steps:
Train the program(Building a model) using a training set with a category for e.g. sports, news,..
Classifier will compute probability for each word, the probability that it makes a document belong to each of the considered categories.
2. Test with a test data set against this model.

10. Clustering
Clustering is the task of grouping a set of objects in such a way that the objects in the same group ( called a cluster) are more similar to each other.
Objects are not predefined.
For e.g. these keywords.
“men’s shoe”
“women’s shoe”
“women’s t-shirt”
“men’s t-shirt”
Can be clustered into 2 categories “shoe” and “t-shirt” or “men” and “women”

11. Regression
It is a measure of the relation between the mean value of one variable (e.g. output) and corresponding values of other variables(e.g. time and cost)
Regression analysis is a statistical process for estimating the relationships among variables.
Regression means to predict the output value using training data.

12. Where it is used?

13. Spam detection

14. Voice-Assistant softwares

15. AI in Gaming