Exam 2021 and resit Flashcards
Difference between cognition and intelligence
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.
Difference btw. bio-inspired and purely computational models
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.
Name and explain 2 Properties of dynamical systems
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.
3 types of cognitive architecture
symbolic, emergent, hybrid
Explain how ACT-R implements parallel information processing and how it implements serial information processing
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
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" )
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
Explain the purpose of MapSpikeSource and MapSpikeSink devices of a transfer function in the NR platform
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
Names of the three main components of biological neuron
Soma, dendrites, axon
2 visual processing streams and which information is computed along them
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?)
2 main schemes for encoding SNN and the main advantages
rate encoding: robustness against noise
time encoding: fast reaction time
State the basic principle of Hebbian learning
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.
Fundamental properties of Hebbian learning?
Saturation: Ovoid unbounded growth of synaptic weights
Competition-> Selection: Avoid weights to converge to the same value
Locality: weights changes dependent on local variables
Describe the statistical process that takes place when Oja’s rule is applied to a dataset
- maximize the variance of the neuron’s output
Name and describe 3 learning paradigms
- 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.
return
sum of future discounted rewards in a Markov reward process
action policy
a function that describes the probability for selecting a specific action conditioned by a state pi(a|s)
state-value function
State value is the expected cumulated discounted reward following a specific policy when being a specific state
reward
numerical signal that implicitly expresses the agent’s goal by encouraging/punishing goal directed/undirected state transitions.
action-value function
q is the expected cumulative and discounted reward following a specific policy when selecting a specific action in a particular state.
approximate RL
the agent predicts values with the help of non-linear function approximators.
Dynamic Programming (bootstrapping? sampling?)
bootstraps, no sampling
-> high width of updating, low depth
Monte Carlo
sampling, no bootstrapping
low width, high depth
Temporal Difference
sampling, bootstrapping
- low width, low depth
Explain GPI
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.
Name and describe the 3 cognitive capabilities
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.
Describe the main characteristics of enactive emergent systems and explain the two principles that they are based on.
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.
Define a multiplication of type chunk and implement the equation 11*3 as declarative knowledge
Define chunk type
(chunk-type multiplication factor1 factor2 product)
(add-dm
(Multiply113:
isa multiplication
factor1 11
factor2 3
product 33))
four main modules of ACT_R
Manual, Visual, Intentional, Declarative
Thalamus
relay and distribution of sensory and motor signals to the different regions of the cortex
white vs. grey matter
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.
Models that are analog
General analog model
McColloch-Pitts model
SNN models
Hodgking-Hudley model
Leaky-integrate and fire model
AdEx model
2 benefits of reducing a neuron model from 4D to 2D
less computational complexity, analytical tractability, analysis in the phase plane are posssible
Why is time-to-first spike more energy efficient on neuromorphic hardware?
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.
Describe BCM theory
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.
structural plasticity
physical creation and deletion of synapses
