A CRC Press FreeBook
Explorations in Artificial
Intelligence and Machine
Learning
,Introduction (Prof. Roberto V. Zicari)
1 - Introduction to Machine Learning
2 - The Bayesian Approach to Machine
Learning
3 - A Revealing Introduction to Hidden
Markov Models
4 - Introduction to Reinforcement
Learning
5 - Deep Learning for Feature
Representation
6 - Neural Networks and Deep Learning
7 - AI-Completeness: The Problem
Domain of Super-intelligent Machines
, READ THE LATEST ON
ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING
WITH THESE KEY TITLES
VISIT
WWW.CRCPRESS.COM/ COMPUTER-SCIENCE-ENGINEERING
TO BROWSE OUR FULL RANGE OF TITLES
SAVE 20% AND GET FREE SHIPPING WITH DISCOUNT CODE ODB18
, Introduction by Prof. Roberto V. Zicari
Frankfurt Big Data Lab, Goethe University Frankfurt
Editor of ODBMS.org
Artificial Intelligence (AI) seems the defining technology of our time.
Google has just re-branded its Google Research division to Google AI as the
company pursues developments in the field of artificial intelligence.
John McCarthy defines AI, back in 1956 like this: "AI involves machines that can
perform tasks that are characteristic of human intelligence".
This Free Book gives you a brief introduction to Artificial Intelligence, Machine
Learning, and Deep Learning.
But, what are the main differences between Artificial Intelligence, Machine
Learning, and Deep Learning?
To put it simply, Machine Learning is a way of achieving AI.
Arthur Samuel's definition of Machine Learning (ML) is from 1959: "Machine
Learning: Field of study that gives computers the ability to learn without being
explicitly programmed".
Typical problems solved by Machine Learning are:
- Regression.
- Classification.
- Segmentation.
- Network analysis.
What has changed dramatically since those pioneering days is the rise of Big
Data and of computing power, making it possible to analyze massive amounts
of data at scale!
AI needs Big Data and Machine Learning to scale.
Machine learning is a way of ?training?an algorithm so that it can learn.
Huge amounts of data are used to train algorithms and allowing algorithms to
"learn" and improve.
Deep Learning is a subset of Machine Learning and was inspired by the
structure and function of the brain.
Explorations in Artificial
Intelligence and Machine
Learning
,Introduction (Prof. Roberto V. Zicari)
1 - Introduction to Machine Learning
2 - The Bayesian Approach to Machine
Learning
3 - A Revealing Introduction to Hidden
Markov Models
4 - Introduction to Reinforcement
Learning
5 - Deep Learning for Feature
Representation
6 - Neural Networks and Deep Learning
7 - AI-Completeness: The Problem
Domain of Super-intelligent Machines
, READ THE LATEST ON
ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING
WITH THESE KEY TITLES
VISIT
WWW.CRCPRESS.COM/ COMPUTER-SCIENCE-ENGINEERING
TO BROWSE OUR FULL RANGE OF TITLES
SAVE 20% AND GET FREE SHIPPING WITH DISCOUNT CODE ODB18
, Introduction by Prof. Roberto V. Zicari
Frankfurt Big Data Lab, Goethe University Frankfurt
Editor of ODBMS.org
Artificial Intelligence (AI) seems the defining technology of our time.
Google has just re-branded its Google Research division to Google AI as the
company pursues developments in the field of artificial intelligence.
John McCarthy defines AI, back in 1956 like this: "AI involves machines that can
perform tasks that are characteristic of human intelligence".
This Free Book gives you a brief introduction to Artificial Intelligence, Machine
Learning, and Deep Learning.
But, what are the main differences between Artificial Intelligence, Machine
Learning, and Deep Learning?
To put it simply, Machine Learning is a way of achieving AI.
Arthur Samuel's definition of Machine Learning (ML) is from 1959: "Machine
Learning: Field of study that gives computers the ability to learn without being
explicitly programmed".
Typical problems solved by Machine Learning are:
- Regression.
- Classification.
- Segmentation.
- Network analysis.
What has changed dramatically since those pioneering days is the rise of Big
Data and of computing power, making it possible to analyze massive amounts
of data at scale!
AI needs Big Data and Machine Learning to scale.
Machine learning is a way of ?training?an algorithm so that it can learn.
Huge amounts of data are used to train algorithms and allowing algorithms to
"learn" and improve.
Deep Learning is a subset of Machine Learning and was inspired by the
structure and function of the brain.
