You are on page 1of 3

Artificial intelligence

 Artificial intelligence is intelligence in machines. It is commonly implemented in computer


systems using program software.

 A very general mental capability that, among other things, involves the ability to reason,
plan, solve problems, think abstractly, comprehend complex ideas, learn quickly and
learn from experience. It is not merely book learning, a narrow academic skill, or test-
taking smarts. Rather, it reflects a broader and deeper capability for comprehending our
surroundings—"catching on," "making sense" of things, or "figuring out" what to do.

 Machine learning is a category within the larger field of artificial intelligence that is
concerned with conferring upon machines the ability to “learn.”

 This is achieved by using algorithms that discover patterns and generate insights from the
data they are exposed to, for application to future decision-making and predictions, a
process that sidesteps the need to be programmed specifically for every single possible
action.

 Deep learning, on the other hand, is a subset of machine learning: it’s the most advanced
AI field, one that brings AI the closest to the goal of enabling machines to learn and think
as much like humans as possible.

 Machine learning is just one approach to reifying artificial intelligence, and ultimately
eliminates (or greatly reduces) the need to hand-code the software with a list of
possibilities, and how the machine intelligence ought to react to each of them.

 Deep Nets are inspired by neurological networks of out brain. We detect complex
patterns by detecting and combining simple ones.
 Deep learning requires a complex architecture that mimics a human brain’s neural
networks in order to make sense of patterns, even with noise, missing details, and other
sources of confusion. While the possibilities of deep learning are vast, so are its
requirements: you need big data, and tremendous computing power.

 If patterns are relatively simple, methods like SVM are perfectly fine, and can be use even
for moderate patterns, even though Deep Nets outperform them. But for complex
patterns the only practical choice is Deep Net.

 The AI that we have right now is called “Weak AI”, or Artificial Narrow Intelligence (ANI).
ANI is limited to a single task and is not self-aware. It can mimic the way humans think
and communicate their ideas (Siri, for example, communicates verbally and through text),
but it’s limited in its ability to actually think like a human.

 Artificial General Intelligence (AGI) are programs that will be able to reason, plan, and
handle complex concepts, and Artificial Super Intelligence (ASI) are programs that are
smarter than all of the collective minds on earth.

 AGI will be able to think at the scale and speed of one human brain, but ASI will be that
times the human population of Earth — 7.3 billion.

Unit One
-An AI program is called “Intelligent Agent”.
Agent’s sensors are tools trough which agent observes state of environment.

-An environment is fully observable if what your agent can sense is completely sufficient to make
the optimal decision (When sensors can see entire state of environment).

-An environment is partially observable if agent can only see a portion of the state of
environment, and in many cases agent needs to acquire internal memory to understand
what the state of environment is.

-Deterministic environment is the environment where your agent’s actions uniquely determine
the outcome.

-Stochastic environment is the environment in which randomness is involved, so that the


outcome cannot be completely determined.

-Discrete environment is the environment in which you have finitely (konačan) action choices
and things you can sense.
-While in Infinite environment there is infinite space of actions or things you can sense.

-In Benign environments, an environment might be random and affect the outcome of actions.

-While Adversarial Environments are contrast of Benign Environments, where agent observes
and tries to counteract what you want to achieve (Used in many games).

Javascript things to learn


There are five types of values: Booleans, Numbers, Strings, Plain Objects, Arrays.

You might also like