2. Humans are limited in their capacity to
process information. This has important
implications for design.
Information is received and responses given
via a number of input and output channels:
visual channel
auditory channel
haptic channel
movement
3. Information is stored in memory:
sensory memory
short-term (working) memory
long-term memory
Information is processed and applied:
reasoning
problem solving
skill acquisition
error
4. Visual perception is a process that interprets
the variations of light that fall on retinas,
and from this input derives descriptions of
the shapes, surface, properties, and
locations of objects.
Visual learning is a teaching and learning
style in which ideas, concepts, data and
other information are associated with images
and techniques.
Two stages in vision
• physical reception of stimulus(motivation)
• processing and interpretation of stimulus
5. mechanism for receiving light and
transforming it into electrical energy
light reflects from objects
images are focused upside-down on retina
retina contains rods for low light vision and
cones for colour vision
ganglion cells (brain!) detect pattern and
movement
6. Size and depth
visual angle indicates how much of view object
occupies (relates to size and distance from eye)
Brightness
subjective reaction to levels of light
affected by luminance of object
measured by just noticeable difference
visual acuity (INSIGHT) increases with luminance as does
flicker(SPARK).
Colour
made up of hue(TYPE), intensity, saturation
cones sensitive to colour wavelengths
blue acuity is lowest
8% males and 1% females colour blind
7. The visual system compensates for:
movement
changes in luminance.
Context is used to resolve ambiguity
READING
Several stages:
visual pattern perceived(observed)
decoded using internal representation of language
interpreted using knowledge of syntax, semantics,
pragmatics(the ways in which context contributes to
meaning).
8. Hearing is one of the major senses and like vision
is important for distant warning and
communication. It can be used to alert, to
communicate pleasure and fear. It is a conscious
appreciation of vibration perceived as sound.
In order to do this, the appropriate signal must
reach the higher parts of the brain. The function
of the ear is to convert physical vibration into an
encoded nervous impulse. It can be thought of as
a biological microphone.
9. Provides information about environment:
distances, directions, objects etc.
Physical apparatus:
outer ear – protects inner and amplifies sound
middle ear – transmits sound waves as
vibrations to inner ear
inner ear – chemical transmitters are released
and cause impulses in auditory nerve
Sound
pitch – sound frequency
loudness – amplitude
timbre – type or quality
10. Auditory learning is a learning style in which a
person learns through listening. An auditory
learner depends on hearing and speaking as a
main way of learning.
Humans can hear frequencies from 20Hz to
15kHz
less accurate distinguishing high frequencies than low.
Auditory system filters sounds
can attend to sounds over background noise.
for example, the cocktail(MIXTURE) party phenomenon.
11. The study of touch communication, technically referred to
as haptic, suggests that touch is perhaps the most
primitive form of communication.
touch is probably the first sense to be used.
Kinesthetic learning (also known as tactile learning) is a learning
style in which learning takes place by the student carrying out a
physical activity, rather than listening to a lecture or watching a
demonstration.
12. Provides important feedback about environment.
May be key sense for someone who is visually WEAK.
Stimulus received via receptors in the skin:
thermoreceptors – heat and cold
nociceptors – pain
mechanoreceptors – pressure
(some instant, some continuous)
Some areas more sensitive than others e.g. fingers.
Kinethesis - awareness of body position
affects comfort and performance.
13. Time taken to respond to stimulus:
reaction time + movement time
Movement time dependent on age, fitness etc.
Reaction time - dependent on stimulus type:
visual ~ 200ms
auditory ~ 150ms
pain ~ 700ms
Increasing reaction time decreases accuracy in
the unskilled operator but not in the skilled
operator.
14. There are three types of memory function:
Sensory memories
Short-term memory or working memory
Long-term memory
15. During every moment of an organism's life, sensory
information is being taken in by sensory receptors and
processed by the nervous system. The information people
received which is stored in sensory memory is just long
enough to be transferred to short-term memory.
Humans have five main senses: sight, hearing, taste, smell,
touch. Sensory memory (SM) allows individuals to retain
impressions of sensory information after the original
stimulus has ceased
Buffers for stimuli received through senses
iconic memory: visual stimuli
echoic memory: aural stimuli
haptic memory: tactile stimuli
Examples
“sparkler” trail
stereo sound
16. TYPES
iconic memory: visual stimuli
Iconic memory is the visual sensory memory (SM)
register pertaining to the visual domain and a
fast-decaying store of visual information.
echoic memory: aural stimuli
Echoic memory represents SM for the auditory
sense of hearing. Auditory information travels as
sound waves which are sensed by hair cells in the
ears.
haptic memory: tactile stimuli
Haptic memory represents SM for the tactile
sense of touch. Sensory receptors all over the
body detect sensations such as pressure,
itching(BURNING), and pain.
17. A common demonstration of SM is a child's ability
to write letters and make circles by twirling a
sparkler at night. When the sparkler is spun fast
enough, it appears to leave a trail which forms a
continuous image. This "light trail" is the image
that is represented in the visual sensory store
known as iconic memory. The other two types of
SM that have been most extensively studied are
echoic memory, and haptic memory; however, it is
reasonable to assume that each physiological sense
has a corresponding memory store. Children for
example have been shown to remember specific
"sweet" tastes during incidental learning trials but
the nature of this gustatory store is still unclear
18. 1. The formation of a SM trace is independent of
attention to the stimulus.
2. The information stored in SM is modality
specific. This means for example, that echoic
memory is for the exclusive storage of auditory
information, and haptic memory is for the
exclusive storage of tactile information.
3. Each SM store represents an huge amount of
detail resulting in very high resolution of
information.
4. Each SM store is very brief and lasts a very
short period of time. Once the SM trace has
decayed or is replaced by a new memory, the
information stored is no longer accessible and
is ultimately lost..
20. Long-term memory is our brain's system for storing,
managing, and retrieving information.
A long-term memory is anything you remember that
happened more than a few minutes ago.
Long-term memories can last for just a few days, or for
many years.
Long-term memories aren't all of equal strength. Stronger
memories enable you to recall an event, procedure, or fact
on demand—for example, that Paris is the capital of France.
Weaker memories often come to mind only through
prompting or reminding.
It is Repository for all our knowledge
slow access ~ 1/10 second
slow decay, if any
huge or unlimited capacity
21.
22. There are many different forms of long-term memories.
The two major subdivisions are explicit memory and implicit
memory.
Explicit memories are those that you consciously
remember, such as an event in your life or a particular
fact.
Implicit memories are those that you do without thinking
about, like riding a bike. you once learned how, and you
remembered how, but now do it without conscious
thought.
23. Episodic Memory: Serial memory of events
Episodic memory is one type of explicit memory.
Episodic memory is autobiographical: it provides us
with a crucial record of our personal experiences. It is
our episodic memory that allows us to remember the
trip we took to Kalam, what we had for dinner last
night, who told us that our friend ali was crminal.
Any past event in which we played a part, and
which we remember as an "episode" (a scene
of events) is episodic.
From the moment of birth, each of us is exposed to a world
full of sensations and information. All of these experiences –
first day in UOS, familiar places, sad farewells -- have the
potential to end up as autobiographical memories.
24. • Another type of explicit memory is semantic memory. It
accounts for our "textbook learning" or general
knowledge about the world. It's what enables us to say,
without knowing exactly when and where we learned,
that a zebra is a striped animal, or that Paris is the major
city in France.
• As with episodic memory, semantic memory ranges from
strong (recall) to weak (familiarity). Unlike episodic
memory, semantic memory is better sustained over time.
We are often able to retain a highly functioning semantic
memory into our 60's–after which it undergoes a slow
decline.
25. Semantic memory structure
provides access to information
represents relationships between bits of information
supports inference
Model: semantic network
inheritance – child nodes inherit properties of parent
nodes
relationships between bits of information explicit
supports inference through inheritance
26.
27. Procedural Memory
Procedural memory is the type of implicit memory that
enables us to carry out commonly learned tasks without
consciously thinking about them. It's our "how to" knowledge.
Riding a bike, tying a shoe and washing dishes are all tasks
that require procedural memory.
Procedural memory likely uses a different part of the brain
than episodic memory—with brain injuries, you can lose one
ability without losing the other. That's why a person who
forgets much about his or her personal life often retains
procedural memory:
28. Priming
Implicit memory can also come about from
priming(training or instructing). You are "primed" by
your experiences; if you have heard something very
recently, or many more times than another thing, you
are primed to recall it more quickly. For example, if you
were asked to name an Pakistani city that starts with
the letters “SW," you would most likely answer SWAT,
unless you have a close personal connection to or
recent experience with another “SW" city (SWABI…)
because you've heard about SWAT more often.
29. Frames were proposed by Marvin Minsky in his 1974 article "A
Framework for Representing Knowledge." A frame is an artificial
intelligence data structure used to divide knowledge into
substructures." Frames are connected together to form a complete
idea. Frames are also an extensive part of knowledge representation
and reasoning schemes.
Each piece of information about a particular frame is held in a slot.
Slots with values for instance of data
Type–subtype relationships
DOG
Fixed
legs: 4
Default
diet: carniverous
sound: bark
Variable
size:
colour
COLLIE
Fixed
breed of: DOG
type: sheepdog
Default
size: 65 cm
Variable
colour
30. Slot Value Type
BOY _ (This Frame)
TYPE Person (parent frame)
SEX Male (instance value)
AGE Under 12 yrs.
(procedural
attachment - sets
constraint)
HOME A Place (frame)
NUM_LEGS Default = 2
(default, inherited
from Person frame)
31. Scripts were developed in the early AI work by Roger Schank, Robert P.
Abelson and their research group, and are a method of representing
procedural knowledge. They are very much like frames, except the
values that fill the slots must be ordered.A script is a structured
representation describing a stereotyped sequence of events in a
particular context. Scripts are used in natural language understanding
systems to organize a knowledge base in terms of the situations that the
system should understand.
Script for a visit to the checkup
Entry conditions: dog ill
vet open
owner has money
Result: dog better
owner poorer
vet richer
Props: examination table
medicine
instruments
Roles: vet examines
diagnoses
treats
owner brings dog in
pays
takes dog out
Scenes: arriving at reception
waiting in room
examination
paying
Tracks: dog needs medicine
dog needs operation
32. It is Representation of procedural knowledge in
condition-action rules
Condition/action rules
if condition is matched
then use rule to determine action.
IF dog is shaking tail
THEN pat dog
IF dog is barking
THEN run away
33. rehearsal
information moves from STM to LTM
total time hypothesis
amount retained proportional to rehearsal time
distribution of practice effect
optimized by spreading learning over time
structure, meaning and familiarity
information easier to remember
34. decay
information is lost gradually
interference
new information replaces old: retroactive
interference
the tendency for the retention of learned material or
skills to be impaired by subsequent learning
old may interfere with new: proactive inhibition
the tendency for earlier memories to interfere with the
retrieval of material learned later
35. recall
information reproduced from memory can be assisted by
hints, e.g. categories, similes
recognition
information gives knowledge that it has been seen
before
39. Deduction:
Deductive reasoning is the kind of reasoning in which,
roughly, the truth of the input propositions (the premises)
logically guarantees the truth of the output proposition
(the conclusion), provided that no mistake has been made
in the reasoning. The premises may be propositions that
the reasoner believes or assumptions that the reasoner is
exploring.
derive logically necessary conclusion from given premises.
e.g. If it is Friday then she will go to work
It is Friday
Therefore she will go to work.
Logical conclusion not necessarily true:
e.g. If it is raining then the ground is dry
It is raining
Therefore the ground is dry
40. (i) If the room is dark then either the light
switch is turned off or the bulb has burned
out;
(ii) The room is dark;
(iii) The light switch is not turned off;
to the conclusion
(iv) The bulb has burned out;
is reasoning deductively. If the three
premises are true, the conclusion is
guaranteed to be true.
41. Induction:the kind of reasoning in which the
truth of the premises need not guarantee the
truth of the conclusion.
generalize from cases seen to cases unseen
e.g. all elephants we have seen have trunks
therefore all elephants have trunks.
Unreliable:
can only prove false not true
… but useful!
42. Abductive reasoning typically begins with an incomplete set of
observations and proceeds to the expected possible explanation
for the set. Abductive reasoning yields the kind of daily decision-
making that does its best with the information at hand is
incomplete.
A medical diagnosis is an application of abductive reasoning:
given this set of symptoms, what is the diagnosis that would best
explain most of them?
reasoning from event to cause
e.g. Sami drives fast when drunk.
If I see Sami driving fast, assume drunk.
Unreliable:
can lead to false explanations
43. Definition: Process of finding solution to
unfamiliar task using knowledge.
Several theories.
1. Gestalt theory:
Gestalt psychologist were answering the claim made by
behaviourists, that problem solving is a matter of reproducing
known responses or trial and errors.
problem solving both productive(creative): and
reproductive(generative).productive draws on insight(vision-
understanding) and restructuring of problem. while
reproductive is based on previous experience.
44. Problem space theory
problem space comprises problem states
problem solving involves generating states using legal
operators
heuristics may be employed to select operators
e.g. means-ends analysis
operates within human information processing system
e.g. STM limits etc.
largely applied to problem solving in well-defined areas
e.g. puzzles rather than knowledge intensive areas
45. Analogy
analogical mapping:
novel problems in new domain?
use knowledge of similar problem from similar domain
analogical mapping difficult if domains are semantically
different
Skill acquisition
skilled activity characterized by chunking
lot of information is chunked to optimize STM
conceptual rather than superficial grouping of problems
information is structured more effectively
46. Types of error
slips
right intention, but failed to do it right
causes: poor physical skill,inattention etc.
change to aspect of skilled behaviour can cause slip
mistakes
wrong intention
cause: incorrect understanding
humans create mental models to explain behaviour.
if wrong (different from actual system) errors can occur
47. Learning − It is the activity of gaining knowledge or
skill by studying, practicing, being taught, or
experiencing something. Learning enhances the
awareness of the subjects of the study.
The ability of learning is possessed by humans, some
animals, and AI-enabled systems. Learning is
categorized as
Auditory Learning − It is learning by listening and
hearing. For example, students listening to recorded
audio lectures.
Episodic Learning − To learn by remembering
sequences of events that one has witnessed or
experienced. This is linear and orderly
48. Motor Learning − It is learning by precise movement
of muscles. For example, picking objects, Writing, etc.
Observational Learning − To learn by watching and
imitating others. For example, child tries to learn by
watching her parent.
Spatial Learning − It is learning through visual
stimuli such as images, colors, maps, etc. For Example,
A person can create roadmap in mind before actually
following the road.
Stimulus-Response Learning − It is learning to
perform a particular behavior when a certain stimulus
is present. For example, a dog raises its ear on hearing
doorbell
49.
50.
51. Voice recognition biometric modality is a
combination of both physiological and
behavioral modalities. Voice recognition is
nothing but sound recognition. It relies on
features influenced by −
Physiological Component − Physical shape,
size, and health of a person’s vocal cord, and
lips, teeth, tongue, and mouth cavity.
Behavioral Component − Emotional status of
the person while speaking, accents, tone,
pitch, pace of talking, mumbling, etc.
52. Voice Recognition is also called Speaker
Recognition. At the time of enrollment, the user
needs to speak a word or phrase into a
microphone. This is necessary to acquire speech
sample of a candidate.
The electrical signal from the microphone is
converted into digital signal by an Analog to Digital
(ADC) converter. It is recorded into the computer
memory as a digitized sample. The computer then
compares and attempts to match the input voice
of candidate with the stored digitized voice
sample and identifies the candidate.
53.
54. There are two variants of voice recognition
− speaker dependent and speaker independent.
Speaker dependent voice recognition relies on
the knowledge of candidate's particular voice
characteristics. This system learns those
characteristics through voice training (or
enrollment).
The system needs to be trained on the users to
accustom it to a particular accent and tone
before employing to recognize what was said.
It is a good option if there is only one user going
to use the system.
55. Speaker independent systems are able to
recognize the speech from different users
by restricting the contexts of the speech
such as words and phrases. These systems
are used for automated telephone
interfaces.
They do not require training the system
on each individual user.
They are a good choice to be used by
different individuals where it is not
required to recognize each candidate’s
speech characteristics
56. It is easy to implement.
Demerits of Voice
Recognition
It is susceptible to quality of microphone and
noise.
The inability to control the factors affecting
the input system can significantly decrease
performance.
Some speaker verification systems are also
susceptible to spoofing attacks through
57. Performing telephone and internet
transactions.
Working with Interactive Voice Response
(IRV)-based banking and health systems.
Applying audio signatures for digital
documents.
In entertainment and emergency services.
In online education systems.
58.
59. Pattern recognition deals with identifying a
pattern and confirming it again. In general, a
pattern can be a fingerprint image, a
handwritten cursive word, a human face, a
speech signal, a bar code, or a web page on the
Internet.
The individual patterns are often grouped into
various categories based on their properties.
When the patterns of same properties are
grouped together, the resultant group is also a
pattern, which is often called a pattern class.
60. Pattern recognition is the science for
observing, distinguishing the patterns of
interest, and making correct decisions
about the patterns or pattern classes.
Thus, a biometric system applies pattern
recognition to identify and classify the
individuals, by comparing it with the
stored templates
61. The pattern recognition technique conducts
the following tasks −
Classification − Identifying handwritten
characters, CAPTCHAs, distinguishing humans
from computers.
Segmentation − Detecting text regions or
face regions in images.
Syntactic Pattern Recognition − Determining
how a group of math symbols or operators
are related, and how they form a meaningful
expression.
62. Pattern recognition deals with identifying a pattern and
confirming it again. In general, a pattern can be a fingerprint
image, a handwritten cursive word, a human face, a speech
signal, a bar code, or a web page on the Internet.
The individual patterns are often grouped into various categories
based on their properties. When the patterns of same properties
are grouped together, the resultant group is also a pattern,
which is often called a pattern class.
Pattern recognition is the science for observing, distinguishing
the patterns of interest, and making correct decisions about the
patterns or pattern classes. Thus, a biometric system applies
pattern recognition to identify and classify the individuals, by
comparing it with the stored templates