Problem 3

Question 1

According to cognitive scientists, how does the mind work ?

Answer 1

People have mental procedures that operate on mental representations to produce thought and action

BUT: different mental pres. foster different mental procedures

ex.: calculations with 1,2,3 are different than with I,II,III

Question 2

Which methods did scientists use to search for the existence of the human mind ?

Answer 2

1. Experimentation with human participants
2. Forming + testing computational models intended to be analogous to mental operations
   - -> to create theoretical framework

Question 3

Central hypothesis of cognitive science

Answer 3

Thinking can be best understood in terms of representational structures in the mind + computational procedures that operate on those structures

–> mind = computer program

Question 4

Computational-representational understanding of mind

CRUM

Answer 4

Refers to the approach to understanding the mind based on the central hypothesis

Question 5

How is a computer an analogy to thinking or using the mind according to CRUM ?

Answer 5

Running a program results from applying algorithms to data structures

–> just like thinking results from applying computational procedures to mental procedures

e.g.: mental representations = data structures; computational structures = algorithms

Question 6

Cognitive theory

Answer 6

Consists of a set of representational structures + a set of processes that operate on these structures

Question 7

Computational model

Answer 7

Interprets these structures + processes by analogy with computer programs that consists of data structures + algorithms

–> makes the cognitive theory more precise this way

Question 8

Software program

Answer 8

Refers to the location where the computational model is implemented in a specific programming language

–> this is done to test the model

ex.: programming language like Java

Question 9

Hardware platform

Answer 9

Refers to the location where the software program runs on

ex.: macintosh, IBM

Question 10

Name the 5 complex criteria for evaluating theories of mental representation that claim to explain thought.

Answer 10

1. Representational power
2. Computational power
3. Psychological plausibility
4. Neurological plausibility
5. Practical applicability

Question 11

Representational power

Answer 11

How much info a particular kind of representation can express

RESULT: Logical relations are difficult to represent in connectionist NWs

Question 12

Computational power

Answer 12

How mental representations account for 3 important kinds of high-level thinking

1. Problem solving
   - -> planning, decision, explanation
2. Learning
3. Language

–> being able to learn from experience

Question 13

Psychological plausibility

Answer 13

Requires accounting for the

a) qualitative capacities of humans
b) quantitative results of psychological experiments concerning these capacities

–> explaining the ways humans accomplish tasks

Question 14

Neurological plausibility

Answer 14

Using neurological techniques to assess high-level cognition + when and where in the brain certain cognitive tasks are performed

e.g.: EEG

RESULT: Real brain NWs are much more complicated, thus connectionist models are only approx. to the behavior of real neurons

Question 15

Practical applicability

Answer 15

Cognitive science should be able to increase the understanding of how students learn

–> + suggest how to teach them better

Question 16

In which way is the stud of mind interdisciplinary ?

Answer 16

It requires the insights + the diversity of methodologies that have been gained by philosophers, psychologists etc

Question 17

Connectionist research

Answer 17

Emphasizes the importance of connections among simple neuron like structures

–> rebound of the computational model, inspired by the brains neuronal structures

e.g.: units = neurons; degree of activation = frequency with which neurons fire

Question 18

Local representations

Answer 18

Refers to a model where neuron-like structures are given an identifiable interpretation in terms of specifiable concepts or propositions

e.g.: one neuron stands for one thing

Question 19

Distributed representations

Answer 19

Refers to a model where NWs learn how to represent concepts or propositions in more complex ways

–> to distribute meaning over complexes of neuron-like structures

THUS: it is trained to accurately respond to stimuli so they can acquire concepts that apply to the stimuli

e.g.: numerous neurons converge to stand for one thing

Question 20

Parallel constraint satisfaction

Answer 20

Managing a cognitive task in a way where ones processing simultaneously satisfies numerous constraints

–> both models can be used to perform this

ex.: managing to create the perfect timetable for each student in a school

=> negative vs positive internal constraints; + external constraint

Question 21

Feedforward network

Distributed representations

Answer 21

Refers to a NW where info flows upward through it

Question 22

Recurrent network

Distributed representations

Answer 22

Refers to a NW where the activation from the output unit feeds back into the input units

Question 23

Synchrony

Answer 23

Refers to a technique that links units that represent associated elements

Question 24

Vector

Answer 24

Refer to lists of numbers that can be understood as the firing rates of groups of neurons

Question 25

What was the broad goal of cognitive science ?

Answer 25

Characterizing the nature of human knowledge --> forms + contents; how knowledge is a) used b) processed c) acquired

Question 26

Cognitive science

Answer 26

Refers to the scientific study of the human mind --> highly interdisciplinary field, combining ideas + methods from a) psychology b) linguistics c) philosophy

Question 27

The analogy to a computer is useful at all 3 stages of the development of cognitive theories. Name the 3 stages + why.

Answer 27

1. Discovery 2. Modification 3. Evaluation --> a) check whether program gets same right answers and makes the same mistakes b) helps to show that postulated representations and processes are realizable plausible

Question 28

What will the degree of activation of the units tell us in local representation ?

Answer 28

By this we can judge about the applicability of the concept --> the truth of proposition

Question 29

External constraint

Answer 29

Everything that one didn't program into the program could be an external constraint --> everything one didn't take into consideration

Question 30

Delta rule

Answer 30

Refers to a gradient descent learning rule for updating the weights of the inputs to artificial neurons in a single layer neural NW --> determines how to update a neural NW during a backpropagation step

Question 31

Back propagation

Answer 31

Can be used to train the NW by adjusting the weights that connect the different units --> involves finding a function (Gradient descent) that best maps/allocates a set of inputs to their correct outputs

Question 32

Gradient descent

Answer 32

Refers to an algorithm that is used to find the set of weights that minimizes the error

Question 33

Process of learning

Answer 33

Minimize its cost function by trying to come as close as possible to the local minimum that is used in the cost function

Question 34

Brain-computer interface | BCI

Answer 34

Uses brain activity to control external devices, by amplifying algorithms --> enables severely disabled patients to interact with the environment

Question 35

Connectionist NWs

Answer 35

Refer to model that can stimulate learning via hebbian learning + back propagation --> useful for understanding psychological processes

Question 36

What do connectionist NWs consist of ?

Answer 36

1. Units - -> have a degree of activations, thus only fire when there is a certain amount of frequency w/ which neurons fire 2. Links - -> can be a) excitatory vs inhibitory b) one way, thus activation flows from one unit to next c) symmetric, activation flows back + forth

Question 37

Positive constraints

Answer 37

Occur when the link between 2 units is excitatory

Question 38

Negative constraints

Answer 38

Occur when the link between 2 units is inhibitory

Question 39

External constraint

Answer 39

Involves linking units to special units --> the special unit refers to one which may affect the unit in a way one did not consider "outsider effect"

Question 40

Negative internal constraints

Answer 40

Are represented by inhibitory connections --> come from incompatibly relaxation, which occurs when 2 actions/goals cannot be satisfied together

Question 41

Positive internal constraints

Answer 41

Are represented by excitatory connections --> come from facilitation relaxation, which occurs if an action facilitates a goal and they both go together

Question 42

Activation functions

Answer 42

Refer to mathematical equations that determine the output of a neural NW based on the a given input --> crucial component of deep learning

Question 43

Graceful degradation

Answer 43

Refers to the gradual deterioration in performance of a distributed system, which is also o a characteristic of the human cognitive system