History & Definition Flashcards

- What is the motivation for building cognitive systems? - What where the first cognitive systems ever built? - How is robotics related to cognitive systems? - What can we expect from cognitive systems in the future?

1
Q

What were the first descriptions of human-like intelligent machines?

A

The first decriptions date back to Greek mythology. Hephaestus, the god of fire, constructed artificial servants made of gold.

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

What are the three laws of robotics?

A

Isaac Asimov

  1. A robot may not injure a human being or, through inaction, allow a human being to come to harm.
  2. A robot must obey the orders given it by human beings except where such orders would conflict with the First Law.
  3. A robot must protect its own existence as long as such protection does not conflict with the First or Second Law.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

What was Elektro?

A

The first humanoid robot, introduced by Westinghouse at the 1939 New York World’s Fair. Elekro could speak, walk, move its head and recognize colors through a photocell.

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

What are Cybernetics?

A

Cybernetics is the science of regulatory systems – the scientific study of control and communication in the animal and the machine.

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

Who coined the term “cybernetics”?

A

Norbert Wiener in 1948

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

What were the first bioinspired robots with “brains”?

A

“Elmer” and “Elsie” by William Grey Walter, two machines of his artificial “robot species”. The robots implement phototaxis and automatically return to their charging station when empty.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

What was Squee?

A

A robotic squirrel developed by Edmund C. Berkeley.

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

Who designed the first Turing-complete computer?

A

Charles Babbage with his Analytical Engine

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

Who designed the first computer to support floating point arithmetic?

A

Konrad Zuse with Z1, Z2, Z3

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

What was the first commercially available microprocessor?

A

The Intel 4004

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

What was Shakey?

A

Shakey was a mobile robot that could navigate in a simplified world with blocks and ramps using computer vision and language processing.

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

What are Expert Systems?

A

An expert system is a computer system that emulates the decision-making ability of a human expert, mainly represented by if-then rules.

Expert systems include domain-specific knowledge for the targeted application, considerably simplifying inference processes.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

What was Mycin?

A

Mycin (1975) was an expert system for identifying infectious bacteria and recommending the appropriate antibiotic drug.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

Why is cognition an unsolved problem?

A

All cognitive systems built so far are highly specialized only for specific niches. Living creatures are more versatile and flexible than any robot ever built.

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

How have cognitive systems changed over time?

A

The first systems were built by neurophysiologists to study the function of the brain. Over time, there has been a shift to a engineering-based view of cognition.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

The is the difference between a system and a process?

A

If you don’t know what it is, call it a system and if you don’t know how it works, call it a process.

17
Q

What is cognition?

A

Cognition is the process involved in the act of knowing, including all processes of consciousness by which knowledge is accumulated, such as perceiving, conceiving and reasoning.

Cognition is the sum of all mechanisms that enable a system to deal with the uncertainty and change within real-world environments.

Cognition is a system-wide property that emerges from the synergy of a repertoire of cognitive functions.

18
Q

What is a system?

A

A regularly interacting or interdependent group of items forming a unified whole

19
Q

What is the purpose of cognition?

A

Cognition enables a system to act autonomously in dynamic real world environments and go beyond its programmed behavior

20
Q

What is a cognitive system?

A

A cognitive system is an autonomous, self-reliant system that can perceive, learn, anticipate events, act and adapt.

A cognitive system is not an isolated entity but is situated in a specific environment within which it acts and interacts.

21
Q

What is the cycle of cognitive processing?

A

In the brain (cognition):
Anticipation -> Assimilation -> Adaptation -> …

Perception -> Cognition -> Action -> …
(sensory organs) (spinal cord, muscles)

22
Q

Cognitive capabilities / principles of human cognition include…

[IMPORTANT!]

A
  • self-reliance: goal-directedness, autonomy, interaction
  • perception & action: interpretation, sensing, anticipation, action
  • adaptation: reaction, learning, anomaly detection
23
Q

What is the Turing Test?

A

A test proposed by Alan Turing in 1950 to determine whether a computer can think, based on an imitation game:

  • An interrogator can communicate with a player A (a man) and a player B (a woman) through written notes
  • The interrogator tries to determine whether player A or player B is the woman
  • Player A is replaced by a computer that tries to make the interrogator believe that it is the woman
  • The computer passes the test when it manages to deceive the interrogator as often as the man

In the more common standard interpretation of the test, the computer only imitates a human and the interrogator is not deceived but only needs to tell computer and human apart

24
Q

What is the Chinese Room Argument?

A

The Chinese room argument holds that a computer cannot be shown to have a “think” regardless of how intelligently or human-like the program may make the computer behave.

Suppose, that this computer performs its task so convincingly that it comfortably passes the Turing test. To all of the questions that the person asks, it makes appropriate responses, such that any Chinese speaker would be convinced that they are talking to another Chinese-speaking human being.

The question is this: does the machine literally “understand” Chinese? Or is it merely simulating the ability to understand Chinese?

25
Q

What is the Uncanny Valley?

A

The physical appearance of a cognitive system has a huge impact on the interaction with humans.

The Uncanny Valley phenomenon states that a steady increase in “humanlikeness” of a robot does not yield a steady increase of familiarity to humans.

The concept suggests that humanoid objects which imperfectly resemble actual human beings provoke uncanny or strangely familiar feelings of eeriness and revulsion in observers.

26
Q

What are some ethical and legal questions regarding Cognitive Systems?

A
  • What about the liability of a cognitive system, e.g. an autonomous car?
  • How can an artificial cognitive system decide which person’s life to save in an unavoidable accident?
  • Can an artificial cognitive system be conscious?
  • Does an artificial cognitive system that acts like a human posses personhood?
27
Q

What are the three waves of AI?

A
  1. handcrafted knowledge (since 1956)
  2. statistical learning (since 1986)
  3. contextual adaptation
28
Q

What is the robotics paradox?

A

Robots excel at well-defined repeatable tasks where they can outperform even the most skilled human workers. (e.g. spot welding)

However, dynamic real-world environments are too complex. (e.g. shopping)

29
Q

What are neurorobotics?

A

Neurorobotics is the study of embodied autonomous neural systems.

Neural systems include

  • brain-inspired algorithms (e.g. connectionist networks)
  • computational models of biological neural networks (e.g. artificial spiking neural networks, large-scale simulations of neural microcircuits)
  • actual biological systems (e.g. in vivo and in vitro neural nets)
30
Q

What are neurorobots?

A

Neurorobots are robotic devices that have control systems based on the principles of nervous systems.

31
Q

How are cognitive systems related to AI/ML?

A

The theory of cognitive systems provides a coherent conceptual framework that accommodates many other disciplines such as AI/ML.

32
Q

What is morphological computation?

A

Morphological computation is the computation performed by the body within the embodiment.

33
Q

What is neuromorphic hardware?

A

Neuromorphic hardware are systems containing circuits to mimic neurobiological architectures present in the nervous system.

34
Q

What is the difference between intelligence and cognition?

A

Cognition is a synergy of several cognitive skills, including intelligence.

35
Q

Examples of cognitive functions

A
  • perception, attention
  • memory, knowledge
  • learning
  • autonomy
  • social cognition
  • consciousness
36
Q

What is embodied cognition?

A

Embodied cognition is the theory that many features of cognition, are shaped by the entire body.

i.e. mind and body are not seperate