Quotes from the book "Master Algorithm" by Pedro Domingos

Five tribes: Domingo divides the field into five contemporary machine-learning paradigms- Evolutionary algorithms, connectionism and neural networks, symbolism, Bayes networks, and analogical reasoning- which he imagines being unified in one future "master algorithm" capable of learning nearly anything.

Here are a few quotes that hit me.

Computers are useless, they can only give you answers. If what you tell them to do is be creative, you get machine learning.

Homo Sapiens is the species that adapts the world to itself instead of adapting itself to the world. Machine learning is the newest chapter in this million-year saga: with it, the world senses what you want and changes accordingly, without you having to lift a finger.

Finding correlation is to machine learning no more than bricks are to houses, and people don't live in bricks.

If every algorithm suddenly stopped working, it would be the end of the world as we know it.

Michelangelo said that all he did was see the statue inside the block of marble and carve away the excess stone until the statue was revealed.

What I cannot create, I do not understand.

Scientists make theories, and engineers make devices. Computer scientists make algorithms, which are both theories and devices.

If machine learning was something you bought in the supermarket, its carton would say: "Just add data".

Technically, machine learning is a subfield of AI.

Computer science has traditionally been all about thinking deterministically, but machine learning requires thinking statistically.

Often, redoing an experiment is easier than finding the paper that is reported.

If cyberwar ever comes to pass, the generals will be human, but the foot soldiers will be algorithms.

The solution is to marry machine learning with game theory. Don't just learn to defeat what your opponent does now; learn to parry what he might do against your learner.

Just a few algorithms are responsible for the great majority of machine-learning applications.

God created not species but the algorithm for creating species.

Machine learning is what you get when the unreasonable effectiveness of mathematics meets the unreasonable effectiveness of data.

Every conceivable problem that can be solved by logical deduction can be solved by a Turing machine.

If a robot had all the same capabilities as a human except learning, the human would soon leave it in the dust.

In 1962, when Kennedy gave his famous moon-shot speech, going to the moon was an engineering problem. In 1662, it wasn't, and that's closer to where AI is today.

Listen to your customers, not to the HiPPO.

Some thinkers are foxes they know many small things and some are hedgehogs they know one big thing.

Machine learning alone will not cure cancer cancer patients will, by sharing their data for the benefit of future patients.

Rationalists believe logical reasoning is the only path to knowledge. Empiricists believe that all reasoning is fallible and that knowledge must come from observation. Pundits, lawyers, and mathematicians are rationalists; journalists, doctors, and scientists are empiricists. In computer science theorists and knowledge engineers are rationalists; hackers and machine learners are empiricists.

How can we ever be justified in generalizing from what we've seen to what we haven't?

The "No free lunch" theorem is that there's no such thing as learning without knowledge.

Pre-conceived notions are bad. But in machine learning, preconceived notions are indispensable.

Machine learning is an unavoidable element of gambling.

Newton's Principle: Whatever is true of everything we've seen is true of everything in the universe.

One of their early findings was that if you buy diapers you are also likely to buy beer.

Consider the little white girl who, upon seeing a Latina baby at the mall, blurted out "Look, Mom, a baby maid". She is NOT racist, she overgeneralized based on her experience.

Learning algorithms are particularly prone to overfitting.

Data mining means "torturing the data until it confesses".

Learning is a race between the amount of data you have and the number of hypotheses you consider.

If it keeps making the same mistakes, the problem is the bias. If there's no pattern to the mistakes, the problem is variance.

Neurons that fire together wire together.

The main limitation of computers compared to brains is energy consumption: your brain uses only about as much power as a small lightbulb, while Watson's supply could light up a whole office building.

Machine learning is the art of making false assumptions and getting away with it. All models are wrong, but some are useful.

Some researchers even argue that the way to create intelligent machines is to build a robot baby and let him experience the world as a human baby does.

How much of your brain does your job use? The more it does, the safer you are.

The greatest benefit of machine learning may ultimately be not what the machine learns but what we learn by teaching them.

Happy learning, whether you are a BOT or a HUMAN !!!