Glasperlenspiel

Question 1

ACT-R – auto-associator

Answer 1

Both have a sub-symbolic level concerning activations. ACT-R: spreading activation, causing
chunks or production rules to be more readily available. Auto-associator: weights between nodes increase by learning.

Question 2

ACT-R – catastrophic degradation

Answer 2

If one production rule in ACT-R is false, the whole system is defective: cannot find a solution or makes a mistake, much like catastrophic degradation.

Question 3

ACT-R – competitive learning

Answer 3

ACT-R: best-fitting production rule is chosen, activated and its position is strengthened.
Competitive learning: the node with highest activity level (most use compared to other nodes)’s associations are strengthened.

Question 4

ACT-R – connectionism

Answer 4

Both have a sub-symbolic level concerning activations. ACT-R: spreading activation, causing
chunks or production rules to be more readily available. Connectionism: weights between nodes increase by learning.

Question 5

ACT-R – delta rule

Answer 5

Both use successive steps to move towards their goal state. ACT-R: solution of sub-goals on
the goal stack incrementally reducing the difference between current/ goal state. Delta rule:
learning and error reduction used to move from current to desired state.

Question 6

ACT-R – graceful degradation

Answer 6

If one production rule in ACT-R is false, the whole system is defective: cannot find a solution
or makes a mistake, the opposite of graceful degradation, in which the system can still
function although one of its parts is broken/ faulty/ not working as it should

Question 7

ACT-R – hippocampus

Answer 7

Hippocampus plays a major role in memory formation. ACT-R’s main components are
procedural and declarative memory

Question 8

ACT-R – human error

Answer 8

ACT-R can be used in order to compensate for human error (such as over-/ underestimation of
risks, biases, etc.) due to advanced processing beyond human capabilities. Some ACT-Rs are
already better at disease diagnosis than humans

Question 9

ACT-R – secondary process cognition

Answer 9

ACT-R: works to achieve goals from the goal stack in a pragmatic way, rather than being
creative. Secondary process cognition: goal-orientated, focused, tries to logically solve
problems, rather than being creative

Question 10

ACT-R – swarm intelligence

Answer 10

Similarly to swarm intelligence, ACT-R is composed of many small units and production
rules to achieve a higher goal, and requires local interactions between members to achieve
higher intelligence. Simple, cue-based rules are followed to create complex behaviour

Question 11

Appraisal theory – automation

Answer 11

Appraisal theory: describes how emotions evolve through comparing individual needs to
external demands. Automation (and judging the level of automation required): compares
individual human/ corporation needs and external demands of the working environment

Question 12

Auto-association – delta rule

Answer 12

Auto-associators aim to produce the same output than the input that they received. Learning
occurs through use of the delta rule, wherein the change in weight of the connections is
determined by the difference between desired and obtained level of activation

Question 13

Auto-association – pattern association

Answer 13

Auto-associators function through pattern association: one stimulus is associated with the
other by presenting the two stimuli simultaneously

Question 14

Auto-association – recurring network

Answer 14

Auto-associators can receive feedback on the input/ outputs they are creating thanks to
recurrent networks, which sends activation from output units back to input neurons within the
same laye

Question 15

Auto-associator – collective intelligence

Answer 15

Features of both include graceful degradation and fault tolerance: ability of a system to keep
functioning despite a part of it not functioning optimally

Question 16

Auto-associator – constraint satisfaction

Answer 16

Auto-associators trained with the delta rule change synaptic weights according to internal
input and external output: creates the same effect as parallel constraint satisfaction, wherein
the goal is to satisfy internal and external input

Question 17

BCI – cognitive enhancer

Answer 17

Both are used to amplify human strengths. BCI: assist humans in developing motor capacities.
Cognitive enhancer: used to amplify pre-existing human skills

Question 18

BCI – dynamic systems

Answer 18

BCI is a type of dynamic system, controlled by pattern association, which turns brain activity
into semantic controls which the machine can read, essentially converting user intent into
device action

Question 19

BCI – human error

Answer 19

BCI is the use of brain signals to control external devices. By detecting an ERN signal in the
EEG signal that is used to control the external device, you can see that the agent is about to
make an error

Question 20

BCI – neuro-ergonomics

Answer 20

Neuro-ergonomics: degree of machine automation is varied depending on operator needs. The
same principle could be applied to BCI, wherein the device can be more or less automated
depending on the mental workload of the individual (and thus their increased probability of
human error)

Question 21

BCI – pattern association

Answer 21

BCI uses pattern association – learning by associating one stimulus with another by
presenting them at the same time – in order to be able to connect brain signals to device
movements

Question 22

Computational power – rule-based learning

Answer 22

The success of rule-based learning in machines depends on the computational power of the
system: increased computation power will increase likelihood of efficient learning

Question 23

Connectionism – multi-agent systems

Answer 23

Connectionism: nodes in a network working together to achieve a goal, parallel activity of
multiple processors. Multi-agent systems: behaviour produced by the sum of its subsystems
modules’ contributions

Question 24

Creativity – competitive learning

Answer 24

Creativity: process of blind variation and selective retention, wherein the “creative” (novel
and useful) idea which is retained and developed on. Competitive learning: the best adapted
and most active node (“winning node”) is strengthened while the other nodes’ connections are
weakened or forgotten

Question 25

CRUM – connectionism

Answer 25

CRUM: computational-representational understanding of mind, which assumes that the mind has structures analogous to those in computer programs, which function by way of connectionism: basic units passing information through connections of varying strengths

Question 26

Delta rule – attractor

Answer 26

Both the delta rule and the attractor work towards a certain preferred output, at which point they are considered stable. Delta rule: settling (no more learning). Attractor: reaching an attractor state (not permanent, but stable for the time being)

Question 27

Delta rule – connectionism

Answer 27

Learning through the delta rule occurs via the principle of connectionism: basic units passing information on through connections of varying strengths

Question 28

Delta rule – neo-Hebbian learning

Answer 28

Both use the same principle of weight change in their connections, which results in learning

Question 29

Delta rule – recurring network

Answer 29

The delta rule can function through use of recurring network, wherein activation from output units is fed back to input neurons in the same layer

Question 30

Delta rule – sub-symbolic learning

Answer 30

Delta rule: learning occurs by adjusting values in order to minimise error. Sub-symbolic learning: learning occurs by adjusting the weights between connections

Question 31

Distributed representation – fault tolerance

Answer 31

Distributed systems can still operate when separate elements fail due to their properties of fault tolerance

Question 32

Dynamic systems – cusp catastrophe

Answer 32

Cusp catastrophe is a branch of bifurcation theory in the study of dynamic systems. The cusp catastrophe explores the behaviour of a dynamic system when faced with a splitting factor which could create divergent behaviour – two behavioural surfaces at one point of the control surface

Question 33

Emotions – connectionism

Answer 33

The HOTCO model for emotions gives each unit/ neuron an emotional valence, which, similarly to connectionism, spreads through a network, resulting in overall emotional assessment

Question 34

Emotions – creativity

Answer 34

Emotions: allow individuals to switch between reactive or deliberative processes. Creativity: forces the switch between divergent and convergent thinking, manifested through the salience network switching between default mode and central executive networks

Question 35

Emotions – cusp catastrophe

Answer 35

Emotions can be a normal or splitting factor in a cusp catastrophe model, as emotions can lead to sudden behavioural changes

Question 36

Emotions – distributed representation

Answer 36

Emotions demonstrate distributed representation through their pattern of activation across many neurons

Question 37

Emotions – dynamic system

Answer 37

ITERA computational model of emotion: bidirectional causal connections between emotions and behavioural intentions: constantly changing and evolving, like a dynamic system. Emotional changes are multicausal (different appraisal variables), as are phase transitions in dynamic systems

Question 38

Emotions – human error

Answer 38

Emotions and human error are both based on a dynamic interaction between the actor and the environment. According to the EMA model, emotions are the result of a causal interpretation of the environment – which changes as they interact with it – and the self. Human error is the result of humans incorrectly interacting with their environment

Question 39

Emotions – predictions

Answer 39

The ITERA computational model of emotion predicts reactions based on the overall coherence of an emotional summary based on individual emotional nodes, consistent with computational predictive models

Question 40

Gradient descent – hill climbing

Answer 40

Gradient descent: seeks to find most profitable/ less costly solution: the local minimum. Hill climbing: seeks to find, step-by-step, the most profitable solution

Question 41

Gradient descent – the oasis problem

Answer 41

Once gradient descent has found the local minimum, it is content to stay there instead of searching for a perhaps lower local minimum: this is the oasis problem

Question 42

Hippocampus – auto-association

Answer 42

Auto-association occurs in the CA3 region of the hippocampus

Question 43

Hippocampus – competitive learning

Answer 43

Competitive learning occurs in the CA1 region of the hippocampus, using lateral inhibition to feedforward models to allow sparseness to remove redundancy and noise

Question 44

Hippocampus – pattern association

Answer 44

Pattern association occurs in the hippocampus, specifically the subiculum, between CA1 (competitive learning) and the entorhinal cortex

Question 45

Hippocampus – GAGE

Answer 45

GAGE and the computational model of the hippocampus are based on real-world examples and give insight on the functioning on the brain, and are neurologically plausible as well as computationally applicable

Question 46

Machine learning – singularity

Answer 46

The singularity principle is the point at which technological (machine) learning will be so advanced that humans will no longer be able to predict or understand what comes next

Question 47

Machine learning – Turing test

Answer 47

The goal of machine learning is to pass the Turing test

Question 48

Predictions – cusp catastrophe

Answer 48

self-explanatory

Question 49

Self-organising system – automation

Answer 49

Neither self-organising systems nor highly automated machine require external input in order to change/ modify/ improve their behaviour

Question 50

Self-organising system - unsupervised learning

Answer 50

Neither require external specifications in order to change/ evolve/ modify themselves

Question 51

Simulated annealing – gradient descent

Answer 51

Simulated annealing: heating up of the system and moving it in less promising directions to seek more promising minimum (local or global), whereas gradient descent seeks to just stay in the local minimum

Question 52

Swarm intelligence – butterfly effect

Answer 52

Swarm intelligence operates by the simple rules rule: minor changes in individual rules can radically alter group behaviour. This is similar to the butterfly, wherein apparently small changes can cause a radical change in the larger picture

Question 53

Swarm intelligence – cusp catastrophe

Answer 53

Catastrophic jump: changes in the independent variable will pass a threshold and result in a large change for the behavioural variable in the cusp catastrophe model. Comparable to bees (swarm intelligence) searching for a new hive: it starts with a few, and then the number grows until it passes a threshold and they all move

Question 54

Swarm intelligence – distributed representation

Answer 54

Swarm intelligence: a large group of individual agents use their local interactions to accomplish a bigger goal, similarly to distributed representation, wherein a group of local neurons interact in order to represent a concept in its entirety

Question 55

Swarm intelligence – graceful degradation

Answer 55

If one of the members of the swarm is not able to function properly, the other members will sustain the system regardless, similarly to the process of graceful degradation, wherein the system is able to keep functioning despite one of its parts not functioning

Question 56

Swarm intelligence – Hebbian learning

Answer 56

Swarm intelligence: the more agents participate in the same action, the more it gets strengthened (e.g. ants walking on a path strengthens the pheromone trail, turning it into the dominant path). Hebbian learning: “what fires together, wires together”: the more often two nodes are simultaneously active, the stronger their connection will be

Question 57

Swarm intelligence – simulated annealing

Answer 57

Swarms (e.g. ants) which end up in a suboptimal pathway (local minimum) can use simulated annealing in the form of oscillating states (ants breaking off from the group to search for new paths) in order to attempt to reach an optimal path (global minimum)

Question 58

Swarm intelligence – sub-symbolic learning

Answer 58

Ants, the main example of swarm intelligence, use sub-symbolic learning through the pheromones that they release, and symbolic learning through learning from other ant’s direct behaviour