Lecture 07 - Neural networks and biology

Question 1

Neural networks and biology

What is this part called?

Answer 1

An apical dendrite

Question 2

Neural networks and biology

What are these called?

Answer 2

Basal dendrites

Question 3

Neural networks and biology

What are basal dendrites?

Answer 3

A basal dendrite is a dendrite that emerges from the base of a pyramidal cell that receives information from nearby neurons and passes it to the soma, or cell body.

Question 4

Neural networks and biology

What are apical dendrites?

Answer 4

An apical dendrite is a dendrite that emerges from the apex of a pyramidal cell.

Question 5

Neural networks and biology

What is this part called?

Answer 5

Soma

Question 6

Neural networks and biology

What is this part called?

Answer 6

Axon

Question 7

Neural networks and biology

Where is the apical dendrite located?

Answer 7

See image

Question 8

Neural networks and biology

Where is the soma located?

Answer 8

See image

Question 9

Neural networks and biolog

Where is the axon located?

Answer 9

See image

Question 10

Neural networks and biology

Where is the basal dendrite located?

Answer 10

See image

Question 11

Neural networks and biology

What are McCulloch and Pitts known for?

Answer 11

Proposing the first computational model of a neuron.

Question 12

Neural networks and biology

Who proposed the first computational model of a neuron?

Answer 12

McCulloch and Pitts

Question 13

Neural networks and biology

When did McCulloch and Pitts first suggest their neuron model?

Answer 13

1943?

Question 14

Neural networks and biology

Describe what’s special about the inputs and outputs of McCulloch-Pitts neurons

Answer 14

They’re boolean values.

Question 15

Neural networks and biology

What’s the activation function of the McCulloch-Pitts neuron?

Answer 15

The step function

Question 16

Neural networks and biology

Are the connections in the McCulloch-Pitts model weighted or unweighted?

Answer 16

Unweighted.

Question 17

Neural networks and biology

Who proposed the perceptron?

Answer 17

Frank Rosenblatt

Question 18

Neural networks and biology

When was the perceptron introduced?

Answer 18

1958

Question 19

Neural networks and biology

What neural model was introduced in 1943?

Answer 19

The McCulloch-Pitts neuron model

Question 20

Neural networks and biology

What neural model was introduced in 1958?

Answer 20

The perceptron

Question 21

Neural networks and biology

Does the perceptron use weighted or unweighted connections?

Answer 21

Weighted

Question 22

Neural networks and biology

What kind of input does the perceptron accept?

Answer 22

Real valued numbers.

Question 23

Neural networks and biology

Which network only accepts boolean inputs? (Perceptron or McCulloch-Pitts model)

Answer 23

The McCulloch-Pitts model

Question 24

Neural networks and biology

Which activation function is used in the perceptron?

Answer 24

Trick question - you can choose.

Question 25

# Neural networks and biology What is the output type of the perceptron?

Answer 25

Boolean outputs. Maybe that's just Rosenblatt's initial model from 1958?

Question 26

# Neural networks and biology Which model is this?

Answer 26

Rosenblatt's perceptron

Question 27

# Neural networks and biology Which model is this?

Answer 27

A McCulloch-Pitts neuron

Question 28

# Neural networks and biology Why do we model neurons? (2)

Answer 28

1) Understanding 2) Inspiration

Question 29

# Neural networks and biology What is a synapse?

Answer 29

A connection point between two neurons.

Question 30

# Neural networks and biology What is a dendrite?

Answer 30

The input channel to a neuron.

Question 31

# Neural networks and biology What is an axon?

Answer 31

Output channels from a neuron.

Question 32

# Neural networks and biology What is transferred through an axon?

Answer 32

Neurotransmitters.

Question 33

# Neural networks and biology What types of ions determine the cell's potential?

Answer 33

Sodium (Na+) and potassium (K+).

Question 34

# Neural networks and biology What are vesicles?

Answer 34

Small fluid-filled containers with neurotransmitters.

Question 35

# Neural networks and biology What are the small fluid-filled containers with neurotransmitters called?

Answer 35

Vesicles.

Question 36

# Neural networks and biology What are vesicles filled with?

Answer 36

Neurotransmitters.

Question 37

# Neural networks and biology What types of synapses exist? (2)

Answer 37

Excitatory and inhibitory.

Question 38

# Neural networks and biology What part of the neuron can be either excitatory or inhibitory?

Answer 38

The synapse.

Question 39

# Neural networks and biology What do weights in an ANN represent (superficially)?

Answer 39

Whether a synapse is excitatory or inhibitory.

Question 40

# Neural networks and biology What happens when a signal comes in from a synapse and arrives at the neuron?

Answer 40

The neuron "integrates" (=sums) it. (Metaphor of charging a capacitor.)

Question 41

# Neural networks and biology What does the feedforward excitation neuron connection look like?

Answer 41

Question 42

# Neural networks and biology What kind of neuron connection is this an example of?

Answer 42

Feedforward excitation.

Question 43

# Neural networks and biology What does the feedforward inhibition neuron connection look like?

Answer 43

Question 44

# Neural networks and biology What kind of neuron connection is this an example of?

Answer 44

Feedforward inhibition

Question 45

# Neural networks and biology What does the convergence/divergence neuron connection look like?

Answer 45

Question 46

# Neural networks and biology What kind of neuron connection is this an example of?

Answer 46

Convergence/divergence

Question 47

# Neural networks and biology What does the lateral inhibition neuron connection look like?

Answer 47

Question 48

# Neural networks and biology What kind of neuron connection is this an example of?

Answer 48

Lateral inhibition

Question 49

# Neural networks and biology (@image missing) What does the feedback/recurrent inhibition neuron connection look like?

Question 50

# Neural networks and biology What kind of neuron connection is this an example of?

Answer 50

feedback/recurrent inhibition

Question 51

# Neural networks and biology What does the feedback/recurrent excitation neuron connection look like?

Answer 51

Question 52

# Neural networks and biology What kind of neuron connection is this an example of?

Answer 52

feedback/recurrent excitation

Question 53

# Neural networks and biology What is synaptic plasticity?

Answer 53

Synaptic plasticity is the change in the connection strength that occurs at synapses, meaning how active or inactive they are.

Question 54

# Neural networks and biology Who coined the term synaptic plasticity?

Answer 54

Donald Hebb

Question 55

# Neural networks and biology When did Donald Hebb coin the term synaptic plasticity?

Answer 55

1949

Question 56

# Neural networks and biology Synapses can change the strength of the signals they send. What is this called?

Answer 56

Synaptic plasticity.

Question 57

# Neural networks and biology What is long-term potentiation? (abbrev. LTP)

Answer 57

Long-term potentiation (LTP) is a persistent increase in synaptic strength following high-frequency stimulation of a chemical synapse.

Question 58

# Neural networks and biology What is it called when synaptic strength increases after high-frequency stimulation of a chemical synapse?

Answer 58

Long-term potentiation (LTP)

Question 59

# Neural networks and biology Who discovered long-term potentiation?

Answer 59

Terje Lømo

Question 60

# Neural networks and biology When did Terje Lømo discover long-term potentiation?

Answer 60

1966

Question 61

# Neural networks and biology Are synapses chemical or electrical?

Answer 61

Both

Question 62

# Neural networks and biology Is chemical or electrical synapses more common?

Answer 62

Chemical

Question 63

# Neural networks and biology Describe Hebbian plasticity

Answer 63

If a pre-synaptic neuron fires shortly before a post-synaptic neuron, their connection is strengthened.

Question 64

# Neural networks and biology Describe the topology of a biological neural network.

Answer 64

Sparse and complex. Not dense, not regular, yet not random.

Question 65

# Neural networks and biology Describe what's done because biological connections are metabolically costly to maintain.

Answer 65

They are pruned.

Question 66

# Neural networks and biology How do neurons communicate?

Answer 66

Via action potentials (AP).

Question 67

# Neural networks and biology How are action potentials generated?

Answer 67

By ions travelling across neural membranes.

Question 68

# Neural networks and biology What is generated when ions travel across neural membranes?

Answer 68

Action potentials.

Question 69

# Neural networks and biology What do conventional ANNs approximate?

Answer 69

Rate coding.

Question 70

# Neural networks and biology Which type of network approximate rate encoding?

Answer 70

Conventional ANNs.

Question 71

# Neural networks and biology Describe the leaky-integrate-and-fire (LIF) model. (4)

Answer 71

1) Spikes are sent into the neuron. 2) The neuron sums all incoming spikes. 3) The neuron "leaks" (the signal decays). 4) If the spike crosses a threshold, a spike is sent out and the neuron reset.

Question 72

# Neural networks and biology What are some "common sense" coding methods for spiking neural networks (SNNs)?

Answer 72

1) Rate coding 2) Time-to-first-spike coding 3) Phase coding 4) Burst coding

Question 73

# Neural networks and biology What is STDP short for?

Answer 73

Spike-time dependent plasticity

Question 74

# Neural networks and biology What are the ways of training SNNs?

Answer 74

1) STDP learning 2) Stochastic STDP 3) ANN-SNN conversion 4) Backpropagation

Question 75

# Neural networks and biology What is neuromorphic hardware?

Answer 75

Hardware for running SNNs.