Student Exam questions Flashcards
cognitivist cognitive systems
Cognitivist cognitive systems are based on the hypothesis that cognition is a form of computation. Cognitive functions are modelled as working computer programs.
emergent cognitive models
In emergent cognitive models, cognition is a continuous self-organisation process that is driven by the interaction between the agent and its environment.
Name seven cognitive capabilities that a system must possess in order to be self-reliant and adaptive, and interact with its environment
Self-reliant
goal-directed
autonomous
interact with other agents
Perception & Action
interpretation
sensing
anticipation
adaption
Adaption
reaction
learning
anomaly detection
Name the four different lobes in the cerebrum and explain what their main cognitive
Frontal lobe: short-term memory, action planning, movement control
Parietal lobe: somatic sensation, body image
Temporal lobe: hearing, learning, memory, emotions
Occipital lobe: vision
Assume that you have a doll company.
Uncanny valley phenomenon states that a steady increase in human-likeness does not yield a steady increase in the familiarity to humans.
- Define what a cognitive system is.
A cognitive system is an autonomous system that can perceive its environment, learn from experience, anticipate the outcome of events, has goal-oriented behaviour and can adapt to changing circumstances.
Define cognition
Cognition is the process of knowing and includes perception and judgement. It includes all processes of consciousness by which knowledge is accumulated like perceiving, recognizing. It is the experience of knowing and different from feeling or willing. It refers to the mind and the body.
components of a cognitive system
Environment (situatedness)
Body (embodiment)
Brain (constraints)
Other Agents (interaction)
cycle of cognitive processing
perception -> cognition (anticipation, assimilation, adaption) -> action
Explain what the neurorobotics platform is and explain the advantages of its usage
The neurorobotics platform is a multidisciplinary approach and tries to unify neuroscience, robotics, and AI. You have simulated robots in a virtual environment controlled by NN. The advantage is that you don’t have to have a physical robot and you can thus save time and money.
Name two software tools that are integrated in the neurorobotics platform
Gazebo: body simulation for robots in virtual environments
OpenSim: modelling and simulation of movement
Explain the function of buffers in ACT-R
Information about the current state of the module is exposed through named buffers. Every buffer stores one chunk and is assigned to exactly one module. Buffers serve as interfaces between modules. Buffers directly process queries about their contents.
Explain a module in ACT-R. Name two features of modules in ACT-R.
Modules represent independent parallel processing units that encapsulate specific functions: every module corresponds to a cognitive function in the brain information processing is independent from other modules
Explain what production is in ACT-R
Production is a statement of a particular contingency that control behavior
Explain what the main purpose of the white matter in the cerebrum is
White matter essentially functions in affecting learning and brain functions, modulating the distribution of action potential, and coordinating communication between the different brain regions.
Name and describe the anatomy of the surface of the cerebral cortex.
Gyri = crests formed by the convoluted surface of the cerebral cortex Sulci = fissures between two neighbouring gyri lobes = on each hemisphere there are two major sulci which divide the cerebral surface into the frontal, parietal, temporal and occipital lobe.
Name two distinctive features of human brain that makes it stand out among other species
neuron morphology: the pyramidal neurons in the human cortex have the most elaborate and spine-rich dendritic trees
Electrical properties of neurons: pyramidal neurons have a low membrane capacity, which enhances signal transmission.
Explain what the Blue Brain Project
Whole brain model that developed a data-driven reconstruction process for cortical microcircuits.
The digital reconstruction is based on experimental data and predictions.
Name and describe the two subsystems of the vertebrate nervous system
Central Nervous System: central information processing system formed by the brain and the spinal cord. It collects and distributes data throughout the body
Peripheral Nervous System: transmits signals between sensory organs, muscles, and internal organs and the CNS
Name two features or properties of the peripheral (autonomic) nervous system
The Peripheral Nervous System is responsible to self-regulation and operates unconsciously. It includes two antagonistic subsystems:
Sympathetic nervous system:
Prepares the organism for stress
Parasympathetic nervous system:
sets the body to resting state and increases digestive functions
Map the nervous system into the perception-cognition-action diagram
Cognition with sub-functions are part of the brain. Perception are sensory organs and action is spinal cord and muscles.
Explain the main purpose of the brainstem. Name the four sections that compose it.
The brainstem connects the cerebrum with the spinal cord.
Four sections: Diencephalon Midbrain Pons Medulla Oblongata
Name three learning rules based on Hebbian learning
Basic Hebb’s rule
Correlation-based rule
Covariance-based rule
Name five levels of modelling the dynamics of biological neurons
Detailed-compartment model Reduced-compartment model Single-compartment model Cascade Models Black-box-models
describe Hodgkin-Huxley Model
- model contains a single compartment and is the basis for conductance-based models
- drawback is computational complexity
- -> phenomenological models are better
Explain the meaning of the statement “Neurons that fire together, wire together”
The synaptic weight between two neurons increases if the two neurons activate simultaneously, and reduces if they activate separately.
Hebbian learning.
neuroplasticity
Neurons can change their morphology, which allows for development and learning
Explain the resting membrane potential of a neuron
It is the equilibrium voltage state between the voltage gradient and the charge gradient
Explain the function of the myelin sheath around nerve fibres.
In the myelinated segments of the axon, signals are transmitted through fast electrotonic conduction. The myelin sheath increases the resistance of the membrane. The action potential is regenerated at gaps in the myelin sheath, the nodes of Ranvier.
Name two different types of neural plasticity and briefly describe them.
Functional plasticity: ability to alter and adapt the functional properties of neurons → biological processes modelled by STDP and hebbian learning.
Structural plasticity: physical creation and deletion of synapses, healing the network → not modelled so far.
Name three methods for avoiding the problem of overfitting
Regularisation: add a regularisation term at the end of your objective (loss) function that punishes model complexity (i.e L2 regularisation) Add more (diverse) training data Data augmentation: when you have not enough data, transform your existing data (i.e in case of an image: crop, shift, flip, noise, salt&pepper)
Max-Pooling
Max pooling (complex cells) are filters applied in Convolutional Neural Networks (CNN) that perform subsampling on the output of a layer by computing the maximum value of a small subset of features.
- reduces dimensionality
- makes network more robust
Define “machine learning” with your own words
Machine Learning: field of study that gives computers the ability to learn without being explicitly programmed. A ML system is composed of a Dataset (S), a model (M), an objective (loss or reward) function (L) and an algorithm A that adjusts M based on S and L.
Explain the advantage of converting the convolutional kernels and inputs of a neural network into the Fourier Space. Explain What the main challenge for this approach is?
Conversion of inputs and kernels into Fourier Space reduces the number of operations required for computing convolutions. The challenge lies in keeping the computational cost for the Fourier Transform low.
Explain the difference between interpolation and regression.
Interpolation; the approximated function should match exactly with all the dataset points (not used for ML predictive tasks OR overfitting if applied to ML)
Regression: the approximated function should minimise a loss function and does not have to match with all train data points: it should generalise (used for predictive tasks).
State the problem of using least squares for linear classification. Explain how support vector machines address this problem
Least Square classification is really sensitive to outliers.
generalisation error by computing a hyperplane that maximises the margin of the classifier, i.e. the smallest distance between the decision boundary and the training samples → insensitive to outliers
Name three learning paradigms.
Supervised learning: data object (with features) and labels associated
Unsupervised learning: data object (with features), no labels needed.
I.e k-means clustering, image segmentation
Reinforcement learning: sequential data and an agent. An agent learns by interactions in the environment (thanks to rewards that are the results of his interactions)
Additional: Semi-supervised learning
Occam’s Razor
Given two models M1 and M2 with equal performance, the simplest model (i.e less model features, less layers in a convolutional neural net…etc) is to be preferred (also called law of parsimony).
. Name and describe the role of the two streams of visual processing
The dorsal stream of visual processing determines an object’s spatial location.
It determines how motor actions are carried out.
The ventral stream determines an object’s identity
Name and describe the three conceptual processing layers in the human visual system.
Low-level-vision → basic image analysis
Mid-level-vision → objects, surfaces
High-level-vision → memory, intention
Name a problem that can not be solved by a single perceptron with a linear activation function. State briefly or draw the reason for that.
XOR problem: the Perceptron learning rule only converges for linearly separable data sets → It therefore cannot classify the XOR dataset correctly.
Explain the difference between on-policy and off-policy learning
The agent is learning on-policy when the behaviour policy and target policy are the same.
The agent is learning off-policy when the behaviour policy differs from the target policy.
“bootstrapping value
Propagating value between consecutive states by iteratively exploiting the recursive relationship that is formulated by the Bellman Equation is denoted as bootstrapping.
Name and describe the two alternating steps that are performed iteratively under the framework of Generalised Policy Iteration.
the general idea of letting policy evaluation and policy improvement processes interact, independent of the granularity and other details of the two processes
operant conditioning
In operant conditioning a subject learns the relationship between a stimulus and its behavior. A stimulus is only presented in response to a certain action of the subject and serves as a reinforcer that increases or decreases the probability of that action.
State the reason behind using a linear activation function in the output layer of a Deep Q-Network.
The goal of Deep Q-Network is to estimate the action value function which is Q value. Therefore the output of DQN shouldn’t be constrained by any activation function → it is just a linear layer.
Name the two main types of modern neuroimaging
Structural and functional neuroimaging. Structural is Magnetic Resonance Imaging (MRI) and Electroencephalography (EEG). Functional is functional MRI, Positron Emission Tomography (PET) and then there is Single Positron Emission Computational Tomography (SPECT).
