Brainscape's Knowledge GenomeTM

Browse over 1 million classes created by top students, professors, publishers, and experts.


See full index

Man and Machine > Task 3 > Flashcards

Task 3 Flashcards

1
Q

What is the main aim of cognitive science ?

A
  • explain how people accomplish various kinds of thinking
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

What is meant by mental representation ? (refer to task 1)

A
  • It is the knowledge in our mind
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

What opperates on mental representations ?

A
  • Mental procedures /computational procedure which activate thoughts and reasoning
  • on mental representations
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

Give an example regarding mental procedure and mental representation:

A
  • The number system is = mental representation

- What kind of number system is the mental procedure (Roman or Arabic)

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

What is the core method of AI ?

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

Repeat: What is meant by CRUM ?

A
  • Thinking can best be understood in terms of representational structures in the mind and computational procedures that operate on those structures
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

What is meant by serial processing ?

A
  • Proccessing one information at a time (computer)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

What is meant by parallel processing ?

A
  • Processing multiple task at a time (brain and new computers)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

What is meant by connectionism ?

A
  • Computational modeling inspired by neuronal structuresof the brain
  • Using Units = Neurons
  • Degree of activation = frequency of which neurons fire
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

What are two types of connectionism models ?

A
  • Local representation (concepts are represented by single nodes) -> using parallel processing
  • Distributed representation (concepts are represented as activation pattern across multiple nodes) -> using parallel processing
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

How does the feedforward model work ?

A
  1. informaion flows upwards trough out the network (it gets passed forward)
  2. Info is not encoded in any particular node but rather distributed over the whole network of nodes
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

What are the two properties of most computational (distributed) model ?

A
  1. Feedforward network

2. Recurrent Network

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

What is meant by a activation fucntion ?

A
  • Mathematical equation that determines the output of a neural network
  • usually between 1 and 0
  • It determines which neuron should fire or not fire based on whether the neurons input is relevant for the output
  • Indirectly it determines the activation of a neuron
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

What is meant by backpropagation ?

A
  • it is the core algorithm of how machine learn, because backpropegation can be used to callculate the negative gradient
  • it uses the delta rule to fid out error in hidden layers
  • You calculate the steps backwards and start with the output layer to identify the error
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

What is the formula for the coast function?

A
  • (x-y)^2…
  • x = output of what the network gives
  • Y = the output you want it to have
  • …= the sum of it
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

What are three ways to adjust a neurons activity ? (How to change a problem identified by the delta rule)

A
  • changing the bais + changing the weights + changing the activation from the previous layers
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

How does the backpropagation determine the gradient ?

A
  • By knowing each desired activty of each neuron and knowing how the activites can be changed
  • We can go step by step from the last layer to the first layer and adjust weights bias in order to identify the negative gradient
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
18
Q

What is meant by the delta rule ?

A
  • Part of backpropagation
  • The rule of changing the weight of a connection
  • it is using the difference between a target/goal activation and an actual obtained activation-> If this is zero than no adjustment needed
  • basically using an error function
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

What is meant by gracefull degradation ?

A
  • Ability of machine or network to maintain limited functionality even when a large portion of it has been destroyed -> the other neuron make up for their work
  • to prevent catastrophic failure
  • Slow loss of performance
  • Important does not account for local distributed models
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
20
Q

What is meant by Brain computer interface ?

A
  • devices that enable its users to interact with computers by means of brain/neuronal activity only
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
21
Q

What types of Brain machine interface are out there ?

A
  • Assitive BCI

- Rehabilitative BCI

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
22
Q

What is meant by Assitive BCI ?

A
  • aims to substitute lost functions such as communication or motor function, via robotic prosthesis
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
23
Q

What is meant by Rehabilitative BCI ?

A
  • restoration (wiederherstellung) of brain function and/or behaviour by manipulation of neurophysiological activity
24
Q

Are BCI scanners invasive or non invasive ? (how can brain activity be meassured ?)

A
  • They are both
  • Non invaisve = EEG/fmri
  • Inavsive = implantation of electrodes
25
Q

What existed before BCI ?

A
  • HCI = Human-computer interfaces
  • Ex: keyboards
    and mouses
26
Q

For which people is BCI gnerally being used and why ?

A
  • Locked in syndrome and disabled people
  • Because they need some sort of reliable muscular control such as eye movement
  • The
    primary users of BCI systems are individuals with mild to severe muscular handicaps (not mental disorder)
  • Spinla cord injuries and strokes
27
Q

Which method is used by the most BCI methods ?

A
  1. EEG (Steady state potentials)

2. Imaging techniques

28
Q

What is the overall goal of a BCI system ?

A
  • to interact with a device
29
Q

Why is an EEG still more used then invasive techniques ?

A
  • beacuse it has high temporal resolution
  • reasonable spatial resolution
  • it is portable
  • It is easy to handle (putting electrodes on the scalp)
30
Q

Which disease might lead to the need of an BCI ?

A
  • Paralysis since it can disconnect the brain from the body
  • No volitional movemnt possible
  • > BCI can restore mobility and independence for people via translating neuronal activty into control signals for the device
31
Q

Name an exmaple where BCI has been proven to work regarding EEG:

A
  • The robotic arm
  • After paralysis due to the help of a BCI system it was possible to perform 3D grap and reach movements
  • signals were decoded from a small, local population of motor cortex neurons
32
Q

What is meant by Locked in syndrome ?

A
  • severely motor-disabled patients become incapable to communicate while being fully conscious and awake
33
Q

Name an exmaple where BCI has been proven to work regarding fmri:

A
  • Seplling device
  • decodes blood oxygenation level-dependent (bold activity) regarding different mental tasks
  • Allows translating any freely chosen answer (letter by letter)
34
Q

How can participants influence Bold activity ? (Three aspects)

A
  • Location of the signal source by performing three different mental tasks
  • Signal onset delay (delaying the start of the mental task for 0s, 10s, or 20s)
  • Signal duration by varying the mental task duration between 10s, 20s and 30s
  • 27 different combinations
35
Q

How does BCI in general work ? (look up again

A
  • Senors (mostly electrodes) measure brain activity
  • Goes to the feature extractor = raw signals into relevant signals
  • Then it goes into the feature translator where signals get tranformed in logical controls
  • Control interface converts logical control to semantic control
  • Goes into the device controller where semantic controls get translated into physical device-specific command (maybe just draw)
36
Q

Based on CRUM what would be a synonym for mental representation ?

A
  • Data structures

- cooking ingredients

37
Q

Based on CRUM what would be a synonym for computational procedure ?

A
  • Algorithm

- cooking instructions

38
Q

What is meant by a cognitive theory ?

A
  • Explains how the brain works

- Needs mental rerpresentations and mental procedures to operate on those

39
Q

What is meant by a cognitive model ?

A
  • makes the structures (mental representations) and mental procedures more precise by interpretating them with a comupter programm which needs data structures and an algorithm
40
Q

What else do we need in order to create an AI, besides a cognitive theory and a cognitive model ?

A
  • A software (java) and a platform a computer
41
Q

What kind of problems can both modles “local representations” and “distributed representation” solve ?

A
  • parallel constraint satisfaction
42
Q

What is meant by parallel constraint satisfaction ?

A
  • simultaneously satisfy numerous constraints
43
Q

What is meant by the feedforward model in the distributed represenatation model?

A
  • information flows upward through the network
  • Information is not encoded in any particular unit but distributed over the whole network (hidden layers)
  • From first input unit row to last row output unit
44
Q

What is meant by recurrent networks ?

A
  • Activation from the output units feeds back into the input unit
45
Q

Evaluate connectionsim in terms of the above mentioned criterias (form of computational model)

A
  • the mental representation in connectionism lacks on:
    1. Representational power since it has difficultys explaining complex logical relations
    2. Neuronlogical plausability: only approximations to the behaviour of real neurons
46
Q

How is in generel a artifical neural network structured ?

A
  • multiple units
  • links (either exitatory or inhibitory)
  • parallel processing
  • Hebbian learning rule
47
Q

What is meant by an invasive BCI ?

A
  • Surgical implantation of electrodes that
    measure neurons’ activity (for relevant
    behavior)
48
Q

What is meant by non invasive BCI?

A
  • Record brain signals from the scalp

- 7 types of brain signals can be detected (steady state potentials and blood oxygenation lvl)

49
Q

What are the 5 assumptions of connectionism?

A
  • Neurons integrate info
  • neurons pass on info about their input levels
  • Brain structures are layered
  • Neurons influence each other depending on the
    strength of their connection
  • Learning changes strength of connection
50
Q

How does the recurrent network work ?

A 
- It states that recurrent network gain activation from output units feeds back into
input units (feeback signal
51
Q

Why are neuronal networks so key for machine learning ?

A
  • Damage resistance and fault tolerance (graceful degredation)
  • Content addressable memory
  • Constraint satisfacion
52
Q

What is meant by content addressable memory ?

A
  • If given one part of a memory, the system will
    activate in a way that more info about the
    memory will be recovered
53
Q

What is meant by constraint satisfaction ?

A
  • As activity flows through the network, all
    neurons influence each other depending on
    their weight, each input can be seen as a
    constraint
  • The newtrok tries to satisfy as many constraint as possible
54
Q

What types of activation function exist ?

A
  • Linear
  • Non linear = Binary or Sigmoid
  • threshold linear
55
Q

What is better linear or non linear activation function ?

A

Linear = Output is propotional to the input, not capable of backpropagation -> No complex input can be handled
- Non linear = Capable of backpropagation -> can handle complex input -> therfore used for deep neuronal network models

56
Q

What is meant by a binary actiavation function?

A
  • It is a threshold based activation function

- you need to surpass a certain lvl

57
Q

What is meant by the coast function?

A
  • It is the error of output in comparison to the desired output

Man and Machine (12 decks)

Brainscape helps you reach your goals faster, through stronger study habits.
© 2024 Bold Learning Solutions. Terms and Conditions