machine learning: what, why & where?

14
Machine Learning: What, Why & Where? CD Athuraliya

Upload: cdathuraliya

Post on 17-Jul-2015

377 views

Category:

Technology


2 download

TRANSCRIPT

Machine Learning:What, Why & Where?

CD Athuraliya

What is AI?

Intelligence: capacity for logic, abstract thought, understanding, self-awareness, communication, learning, emotional knowledge, memory, planning, creativity and problem solving.

Artificial Intelligence: the science and engineering of making intelligent machines, especially intelligent computer programs.

Artificial Intelligence

Artificial Neural NetworksGenetic AlgorithmsExpert SystemsFuzzy LogicHeuristic Search…Machine learning

We need them to have/do,- knowledge, reasoning, problem solving, perception, learning,

planning, robotics

Machine Learning

Type of artificial intelligence (AI) that provides computers with the ability to learn without being explicitly programmed.

Machine learning focuses on the development of computer programs that can teach themselves to grow and change when exposed to new data.

Search through data to look for patterns, uses that data to improve the program's own understanding.

Machine Learning

Supervised learning- algorithms are trained on labelled examples

Unsupervised learning- algorithms operate on unlabelled examples

Semi-supervised learning- combines both labeled and unlabelled

Reinforcement learning- learning by interacting with an environment

Association rule learning- discovering interesting relations in large databases

Deep learning- discover multiple levels of representation with higher-level, more

abstract features defined

K-means clustering

Apriori algorithm

Applications

Pattern recognitionNatural language processingData miningRoboticsFace detectionSpam filteringTopic spotting

More familiar (probably more interesting) stuff

Google Translate

https://translate.google.lk/

Google Translate

Free translation service that provides translations between different languages

Can translate words, sentences and web pages between any combination of supported languages

Looks for patterns in hundreds of millions of documents to help decide on the best translation for you

By detecting patterns in documents that have already been translated by human translators

Google Translate can make intelligent guesses as to what an appropriate translation should be

“On the other hand, if we build an AI agent today and tell it to evolve its utility function, how can we assure that it won’t reason that ‘Humans think it is moral to kill annoying insects, in part because insect brains are so primitive. But human brains are primitive compared to my powers, so it must be moral for me to kill humans.’” - Stuart J. Russell

That’s it!

Thanks. :)