Artifical Intelligence

by Rinto Jose

Tuesday, 1st Sep 2015 rinto.jose@tcs.com Oh hey, these are some notes. They'll be hidden in your presentation, but you can see them if you open the speaker notes window (hit 's' on your keyboard).

What is AI?

Artificial intelligence (AI) is the intelligence exhibited by machines or software. -- Wikipedia

The science of making machines that:

Think like people

Act like people

Think rationally

Act rationally

Rational: maximally achieving pre-defined goals
Rational: only concerns what the decisions are made (not the thought process)

Where are we now?

Can we build an AI machine that can:

Play a decent game of table tennis? Drive safely along a curving mountain road? Drive safely along Indian roads? Buy a week's worth of groceries on the web? Buy a week's worth of groceries at Lulu Hyper market Discover and prove a mathematical theorem? Converse successfully with another person for an hour? Perform a surgical operation? Put away the dishes and fold the laundry? Translate spoken Chinese into spoken English in real time? Write an intentionally funny story?

Research Areas

Immediate goals

Reasoning and problem solving

Knowledge representation

Planning

Natural language processing

Machine learning

Machine perception, Computer vision and Speech recognition

Motion and manipulation - Robotics

Long-term goals

Emotion intelligence, Social intelligence, Creativity, and General intelligence.

Natural Language Processing

Speech Technologies

Automatic Speech Recognition (ASR)

Text-to-speech synthesis (TTS)

Dialog Systems

Language Processing

Question answering

Search Engine

Text classification (Sentiment analysis, Spam filtering)

Machine translation

Machine Learning

What is ML?

Learning from history (data) Uses pattern recognition Overlaps with computational statistics and other fields of AI

Applications

Spam filtering Optical character recognition (OCR) Search engines Exploratory data analysis Predictive analytics Machine perception, Computer vision and Speech recognition Text classification (Sentiment analysis, Spam filtering)

Movie Recommendation ML

Movie:

Action Comedy Crime Biography .. .. 90's Will Smith .. ..

User:

Action Comedy Crime Biography .. .. 90's Will Smith .. ..

User Rating 4.31

Calculated Rating 0.00

Essentials of Machine Learning

You must have data

A pattern must exist

The pattern may not be mathematically identifiable

Types of Learning

Supervised learning

The computer is presented with example inputs and their desired outputs, given by a "teacher", and the goal is to learn a general rule that maps inputs to outputs.

Unsupervised learning

No labels are given to the learning algorithm, leaving it on its own to find structure in its input. Unsupervised learning can be a goal in itself (discovering hidden patterns in data) or a means towards an end.

Reinforcement learning

A computer program interacts with a dynamic environment in which it must perform a certain goal (such as driving a vehicle), without a teacher explicitly telling it whether it has come close to its goal or not. Another example is learning to play a game by playing against an opponent.

Supervised Learning

Algorithms

Linear classifiers (eg: Naive Bayes classifier)

Quadratic classifiers

Artificial neural network (eg: Backpropagation)

Decision trees

Hidden Markov models

Applications

Analytical learning

Spam classification

Data Pre-processing and cleansing

Predictive modeling

Unsupervised Learning

Algorithms

Expectation–maximization algorithm

Multilinear subspace learning

Applications

Data clustering (exploratory data mining)

Image analysis

Computer vision

Reinforcement Learning

D E M O

Reinforcement Learning

Algorithms

Expectation–maximization algorithm

Multilinear subspace learning

Applications

Data clustering (exploratory data mining)

Image analysis

Computer vision