Artificial Intelligence Flashcards

You may prefer our related Brainscape-certified flashcards:
0
Q

Programs

A

Implement algorithms

–written in specific programming languages

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
1
Q

Algorithm

A

Sequence of instructions, effective procedure

–independent of programming language

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

ANN

A

Artificial Neural Network

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

Parts of a ANN (neural net)

A

Nodes, links

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

Nodes

A
  • activation value
  • thresholds (nodes can fire if input exceeds threshold)
  • units in a network
  • like cell body of a neuron
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

Links

A
  • connections b/w nodes
  • weights
  • like synapses of neuron
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

Weights

A

Number associated with that link

  • can be positive or negative
  • numerical value b/w -1 and 1
  • closer to |1| = heavier weight
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

Basis Function

A

Receives inputs, calculates summation (like cell body of neuron)

Sj = (sum) aiwji

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

Inputs

A

Each connected node’s activation value multiplies by connection weight of link b/w the two

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

Identity function

A

When activation same as input

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

Simple network (feed forward)

A

Flow of activation = forward only

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

Hidden layer

A

Only communicate with units INSIDE network (don’t get external input or send output outside)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

Backpropogation

A
  • initial response compared to target response
  • target provided by “teacher”
  • actual result subtracts from target result
  • -error signal (target - actual)
  • -feeds back to network
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

Definition of a robot (4 things)

A
  • mechanical creature, can function w/ no operator
  • can adapt to changing environment
  • can function even if some parts break
  • can move and change things
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

hard stuff

A

Can robot do things like have conversation, interact in human like way?

Top to bottom: start w/ language, interaction

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

Easy stuff

A

Movement in an environment

Bottom to top: start w/ interaction w/ environment

16
Q

The uncanny valley

A

(Hard stuff)

  • as we get closer to a robot being more human like…things get creepier
  • -more human like, more positive response
  • -gross
  • -positive
17
Q

Mobots

A

Mobile robots

  • modeled on organisms (e.g. Cockroach)
  • adapt to uneven terrain
18
Q

Early robotic systems based on 3 primitive functions

A
  1. Sense
    - takes data from sensors
  2. Plan
    - takes sense data, creates task to execute
  3. Act
    - sends commands to manipulator
19
Q

Reactive paradigm

A

Get rid of planning, just sense and act

20
Q

Subsumption architecture

A

Planning is subsumed (absorbed) by sense/act interaction

21
Q

Series of layers for different behaviors

A

Layer 1: use sonar to detect obstacles, move away from them

Layer 2: wander around