Transcript Lecture 5 , Aug - Computer Science

Exposition on
Cyber Infrastructure
and
Big Data
Mehdi Ghayoumi
Kent State University
Computer Science Department
Summer 2015
[email protected]
Learn
A cognitive system learns. The system leverages data to
make inferences about a domain, a topic, a person, or an
issue based on training and observations from all
arieties, volumes, and velocity of data.
Model
To learn, the system needs to create a model or representation of
a domain (which includes internal and potentially external data)
and assumptions that dictate what learning algorithms are used.
Understanding the context of how the data fits into the model is
key to a cognitive system.
Generate hypotheses
A cognitive system assumes that there is not a single correct
answer. The most appropriate answer is based on the data
itself. Therefore, a cognitive system is probabilistic. A
hypothesis is a candidate explanation for some of the data
already understood. A cognitive system uses the data to train,
test, or score a hypothesis.
Individual (between the ears) including mental processes and
structures in a given person’s brain.
Extended (in the hand) including objects that we think, learn
and create with. For example, an artist’s favorite paint brush
or an architect’s model of a building.
Group
(among the heads) including any collection of
individuals. For example, a partnership, product development
team or therapy group.
Machine (in a black box) including hardware and software
that automates one or more mental processes or structures.
For example, the buzzer on your clothes dryer or an expert
system a car mechanics uses to diagnosis a problem.
Emergent (beyond the heads) including a group and/or
machine intelligence the delivers a new mental state or level
of performance. For example, a prediction market that
forecasts a presidential election or the success of a new
product better than any individual.

Philosophy

Computer Science - Artificial Intelligence

Psychology – Cognitive Psychology

Linguistics

Neuroscience

Anthropology, Psychiatry, Biology, Education, ...
Blueprint
for
intelligent
agents.
It
proposes
(artificial)
computational processes that act like cognitive systems (human)
An approach that attempts to model
behavioral as well as
structural properties of the modeled system.
Aim : to model systems that accounts for the whole of cognition,
i.e., systems with Artificial Consciousness – which can not only
respond but also think, perceive and believe like a human !
Artificial Consciousness is broadly classified as access and
phenomenal consciousness.
Brain processes neural impulses from
the eyes and determines that this image is
physically unstable – pattern recognizability.
What about pain, anger, motivation, attention, feeling of
relevance, modeling other people's intentions, anticipating
consequences of alternative actions, or inventing ?
 Newell introduces Soar, an architecture for general
cognition.
 Soar is the first problem solver to create its own sub goals
and learn continuously from its own experience.
 Soar has the ability to operate within the real-time
constraints of intelligent behaviour, such as immediateresponse and item-recognition tasks.
 Soar is a symbolic cognitive architecture.
 An AI programming language.
 It provides a (cognitive) architectural framework, within which
you can construct cognitive models.
It can be considered as an integrated architecture for
knowledge-based problem solving, learning, and interaction
with external environments.
 Soar can be divided into 3 levels :
 Memory Level
 Decision Level
 Goal Level
Digital computers are
• Made from silicon
• Accurate (essentially no errors)
• Fast (nanoseconds)
• Execute long chains of serial logical operations (billions)
• Irritating to humans
Brains are
• Made from carbon compounds
• Inaccurate (low precision, noisy)
• Slow (milliseconds, 106 times slower)
• Execute short chains of parallel alogical associative
operations (perhaps 10 operations)
• Understandable to humans
Huge disadvantage for carbon: more than 1012 in the product of
speed and power. But we do better and faster in many tasks:
• speech recognition,
• object recognition,
• face recognition,
• motor control
• most complex memory functions,
• information integration.
Implication: Cognitive “software” uses only a few but very powerful
1. Engineering:
Many of the important practical computer applications of the next
decade will be cognitive:
·
Language understanding.
·
Internet search.
·
Cognitive data mining.
·
Decent human-computer interfaces.
We feel it will be necessary to have a brain-like architecture to
run these applications efficiently.
2. Kinship Recognition, Human Factors:
To be recognized as intelligent by humans, a machine has to
have a somewhat human-like intelligence.
There may be many kinds of intelligence, but we can only
understand and communicate with one of them!
Successful human-computer interactions will require a brainlike computer doing cognitive computation.
3. Personal:
A technological vision: In 2050 the personal computer you buy in Wal-Mart
will have two CPU’s with very different architecture:
First, a traditional von Neumann machine that runs spreadsheets, does
word processing, keeps your calendar straight, etc. What they do now.
Second, a brain-like chip To handle the interface with the von Neumann
machine, Give you the data that you need from the Web or your files
http://www.magicleap.com/#/home
http://persci.mit.edu/demos/gaz/main-frameset.html
https://www.youtube.com/watch?v=C5Xnxjq63Zg
https://www.youtube.com/watch?v=77pnVFLkUjM
Thank you!