Exam 2021 and resit

Question 1

Difference between cognition and intelligence

Answer 1

Cognition is a
- global process at the system
- that integrates many different processing modalities.
Special cognitive skills such as intelligence, learning, memory etc are constituents and synergies of a cognitive system.

Question 2

Difference btw. bio-inspired and purely computational models

Answer 2

Bio-inspired models: Implement cognitive functions by replicating known or hypothesized mechanisms of cognitive processing from biological organisms.
Computational models: Implement cognitive functions based on a functional view of the system without any reference to biology.

Question 3

Name and explain 2 Properties of dynamical systems

Answer 3

Dissipation: the number of reachable states reduces over time
Non-equilibrium system: stable functions require external energy supply
Non-linearity: Complex behavior can emerge from a small set of state parameters
Collective variables: the system is represented by a small set of state variables.

Question 4

3 types of cognitive architecture

Answer 4

symbolic, emergent, hybrid

Question 5

Explain how ACT-R implements parallel information processing and how it implements serial information processing

Answer 5

Parallel Information Processing:

• information processing within modules can be parallel to support high-dimensional data streams
• different modules process data in parallel independently from each other

Serial Information Processing.

• every module buffer can store only a single chunk
• in each cycle of the production system exactly one rule fires

Question 6

Describe the buffer test and buffer action of the following production rule:

(p type
=goal>
isa goal
state enter-number
==> 
\+Manual>
CMD PRESS-KEY
KEY "2"
)

Answer 6

Test if the goal buffer 
holds a chunk of type goal
and if the state is enter-number
then send a buffer request
to the manual module
to press to key 2

Question 7

Explain the purpose of MapSpikeSource and MapSpikeSink devices of a transfer function in the NR platform

Answer 7

MapSpikeSink: reads out spikes from the SNN and coverts them into float values
MapSpikeSource: Creates spikes from a float value that is fed into the SNN

Question 8

Names of the three main components of biological neuron

Answer 8

Soma, dendrites, axon

Question 9

2 visual processing streams and which information is computed along them

Answer 9

Dorsal stream: About the location of the object (Where?) In a more recent view also about how motor functions take place (How?)
Ventral stream: About what the identity of the item ist (What?)

Question 10

2 main schemes for encoding SNN and the main advantages

Answer 10

rate encoding: robustness against noise

time encoding: fast reaction time

Question 11

State the basic principle of Hebbian learning

Answer 11

When axon of cell A is near enough to cell B and persistently or repeatedly takes part in firing to it then some growth process takes place in one or both cells so that A’s efficiency is increased.

Question 12

Fundamental properties of Hebbian learning?

Answer 12

Saturation: Ovoid unbounded growth of synaptic weights
Competition-> Selection: Avoid weights to converge to the same value
Locality: weights changes dependent on local variables

Question 13

Describe the statistical process that takes place when Oja’s rule is applied to a dataset

Answer 13

• maximize the variance of the neuron’s output

Question 14

Name and describe 3 learning paradigms

Answer 14

• unsupervised learning: learning of statistical regularities in the input data with no labels
• supervised learning:
  learn the mapping between input and output data with predefined labels
• reinforcement learning: learning which action to chose in a certain situation in order to maximize an external reward signal through interaction with the environment.

Question 15

return

Answer 15

sum of future discounted rewards in a Markov reward process

Question 16

action policy

Answer 16

a function that describes the probability for selecting a specific action conditioned by a state pi(a|s)

Question 17

state-value function

Answer 17

State value is the expected cumulated discounted reward following a specific policy when being a specific state

Question 18

reward

Answer 18

numerical signal that implicitly expresses the agent’s goal by encouraging/punishing goal directed/undirected state transitions.

Question 19

action-value function

Answer 19

q is the expected cumulative and discounted reward following a specific policy when selecting a specific action in a particular state.

Question 20

approximate RL

Answer 20

the agent predicts values with the help of non-linear function approximators.

Question 21

Dynamic Programming (bootstrapping? sampling?)

Answer 21

bootstraps, no sampling

-> high width of updating, low depth

Question 22

Monte Carlo

Answer 22

sampling, no bootstrapping

low width, high depth

Question 23

Temporal Difference

Answer 23

sampling, bootstrapping

- low width, low depth

Question 24

Explain GPI

Answer 24

Almost every RL algorithm implements the mechanisms of two alternating steps to evaluate an optimal policy

• policy evaluation: evaluation of a value function depending on a policy
• policy improvement: improving the policy by acting greedily on the value function

Both depend on each other so both steps need to be performed iteratively until an optimal policy is found.

Question 25

Name and describe the 3 cognitive capabilities

Answer 25

Self-reliance: A cs must be able to act in and interact with its environment self-reliantly, purposefully, and independently.
Perception and action: A sc must be able to perceive its environment, make sense of its perceptions, and predict future events.
Adaption: A cs must be able to adapt to changes of itself, of others, and within the environment.

Question 26

Describe the main characteristics of enactive emergent systems and explain the two principles that they are based on.

Answer 26

An enactive cs makes sense of its env. by interaction with it.

Ontogeny: development. The system is structurally coupled with the environment through sense-making and generates its own specific epistemology by capturing the regularities of interaction.

Phylogeny: The interaction between the system and its environment is structurally determined by the innate embodied physical and cognitive capabilities.

Question 27

Define a multiplication of type chunk and implement the equation 11*3 as declarative knowledge

Answer 27

Define chunk type
(chunk-type multiplication factor1 factor2 product)

(add-dm 
   (Multiply113:
       isa multiplication
       factor1 11
       factor2 3
       product 33))

Question 28

four main modules of ACT_R

Answer 28

Manual, Visual, Intentional, Declarative

Question 29

Thalamus

Answer 29

relay and distribution of sensory and motor signals to the different regions of the cortex

Question 30

white vs. grey matter

Answer 30

the cerebral cortex, also called grey matter, is the folded outer layer of the cerebrum that is mainly comprised of cell bodies.
The inner part of the cerebrum, the white matter, is a core of nerve fibers that connect the cortical regions.

Question 31

Models that are analog

Answer 31

General analog model

McColloch-Pitts model

Question 32

SNN models

Answer 32

Hodgking-Hudley model
Leaky-integrate and fire model
AdEx model

Question 33

2 benefits of reducing a neuron model from 4D to 2D

Answer 33

less computational complexity, analytical tractability, analysis in the phase plane are posssible

Question 34

Why is time-to-first spike more energy efficient on neuromorphic hardware?

Answer 34

because it needs to simulate a shorter time period and less spikes need to be sent via the communication grid compared to rate-based encoding.

Question 35

Describe BCM theory

Answer 35

These rules include threshold variables. If the activity of the cell is higher than the threshold then the weight increases, but if it is lower than the weight decreases.
These rules include a second equation governing the dynamics of the variable threshold.

Question 36

structural plasticity

Answer 36

physical creation and deletion of synapses