Brainscape's Knowledge GenomeTM

Browse over 1 million classes created by top students, professors, publishers, and experts.


See full index

ACIT4610 - Evolutionary AI > Lecture 07 - Neural networks and biology > Flashcards

Lecture 07 - Neural networks and biology Flashcards

1
Q

Neural networks and biology

What is this part called?

A

An apical dendrite

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

Neural networks and biology

What are these called?

A

Basal dendrites

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

Neural networks and biology

What are basal dendrites?

A

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.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

Neural networks and biology

What are apical dendrites?

A

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

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

Neural networks and biology

What is this part called?

A

Soma

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

Neural networks and biology

What is this part called?

A

Axon

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

Neural networks and biology

Where is the apical dendrite located?

A

See image

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

Neural networks and biology

Where is the soma located?

A

See image

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

Neural networks and biolog

Where is the axon located?

A

See image

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

Neural networks and biology

Where is the basal dendrite located?

A

See image

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

Neural networks and biology

What are McCulloch and Pitts known for?

A

Proposing the first computational model of a neuron.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

Neural networks and biology

Who proposed the first computational model of a neuron?

A

McCulloch and Pitts

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

Neural networks and biology

When did McCulloch and Pitts first suggest their neuron model?

A

1943?

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

Neural networks and biology

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

A

They’re boolean values.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

Neural networks and biology

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

A

The step function

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

Neural networks and biology

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

A

Unweighted.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

Neural networks and biology

Who proposed the perceptron?

A

Frank Rosenblatt

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
18
Q

Neural networks and biology

When was the perceptron introduced?

A

1958

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

Neural networks and biology

What neural model was introduced in 1943?

A

The McCulloch-Pitts neuron model

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
20
Q

Neural networks and biology

What neural model was introduced in 1958?

A

The perceptron

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
21
Q

Neural networks and biology

Does the perceptron use weighted or unweighted connections?

A

Weighted

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
22
Q

Neural networks and biology

What kind of input does the perceptron accept?

A

Real valued numbers.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
23
Q

Neural networks and biology

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

A

The McCulloch-Pitts model

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
24
Q

Neural networks and biology

Which activation function is used in the perceptron?

A

Trick question - you can choose.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
25
Q

Neural networks and biology

What is the output type of the perceptron?

A

Boolean outputs.

Maybe that’s just Rosenblatt’s initial model from 1958?

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
26
Q

Neural networks and biology

Which model is this?

A

Rosenblatt’s perceptron

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
27
Q

Neural networks and biology

Which model is this?

A

A McCulloch-Pitts neuron

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
28
Q

Neural networks and biology

Why do we model neurons? (2)

A

1) Understanding
2) Inspiration

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
29
Q

Neural networks and biology

What is a synapse?

A

A connection point between two neurons.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
30
Q

Neural networks and biology

What is a dendrite?

A

The input channel to a neuron.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
31
Q

Neural networks and biology

What is an axon?

A

Output channels from a neuron.

32
Q

Neural networks and biology

What is transferred through an axon?

A

Neurotransmitters.

33
Q

Neural networks and biology

What types of ions determine the cell’s potential?

A

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

34
Q

Neural networks and biology

What are vesicles?

A

Small fluid-filled containers with neurotransmitters.

35
Q

Neural networks and biology

What are the small fluid-filled containers with neurotransmitters called?

A

Vesicles.

36
Q

Neural networks and biology

What are vesicles filled with?

A

Neurotransmitters.

37
Q

Neural networks and biology

What types of synapses exist? (2)

A

Excitatory and inhibitory.

38
Q

Neural networks and biology

What part of the neuron can be either excitatory or inhibitory?

A

The synapse.

39
Q

Neural networks and biology

What do weights in an ANN represent (superficially)?

A

Whether a synapse is excitatory or inhibitory.

40
Q

Neural networks and biology

What happens when a signal comes in from a synapse and arrives at the neuron?

A

The neuron “integrates” (=sums) it.

(Metaphor of charging a capacitor.)

41
Q

Neural networks and biology

What does the feedforward excitation neuron connection look like?

A
42
Q

Neural networks and biology

What kind of neuron connection is this an example of?

A

Feedforward excitation.

43
Q

Neural networks and biology

What does the feedforward inhibition neuron connection look like?

A
44
Q

Neural networks and biology

What kind of neuron connection is this an example of?

A

Feedforward inhibition

45
Q

Neural networks and biology

What does the convergence/divergence neuron connection look like?

A
46
Q

Neural networks and biology

What kind of neuron connection is this an example of?

A

Convergence/divergence

47
Q

Neural networks and biology

What does the lateral inhibition neuron connection look like?

A
48
Q

Neural networks and biology

What kind of neuron connection is this an example of?

A

Lateral inhibition

49
Q

Neural networks and biology

(@image missing) What does the feedback/recurrent inhibition neuron connection look like?

A
50
Q

Neural networks and biology

What kind of neuron connection is this an example of?

A

feedback/recurrent inhibition

51
Q

Neural networks and biology

What does the feedback/recurrent excitation neuron connection look like?

A
52
Q

Neural networks and biology

What kind of neuron connection is this an example of?

A

feedback/recurrent excitation

53
Q

Neural networks and biology

What is synaptic plasticity?

A

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

54
Q

Neural networks and biology

Who coined the term synaptic plasticity?

A

Donald Hebb

55
Q

Neural networks and biology

When did Donald Hebb coin the term synaptic plasticity?

A

1949

56
Q

Neural networks and biology

Synapses can change the strength of the signals they send. What is this called?

A

Synaptic plasticity.

57
Q

Neural networks and biology

What is long-term potentiation? (abbrev. LTP)

A

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

58
Q

Neural networks and biology

What is it called when synaptic strength increases after high-frequency stimulation of a chemical synapse?

A

Long-term potentiation (LTP)

59
Q

Neural networks and biology

Who discovered long-term potentiation?

A

Terje Lømo

60
Q

Neural networks and biology

When did Terje Lømo discover long-term potentiation?

A

1966

61
Q

Neural networks and biology

Are synapses chemical or electrical?

A

Both

62
Q

Neural networks and biology

Is chemical or electrical synapses more common?

A

Chemical

63
Q

Neural networks and biology

Describe Hebbian plasticity

A

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

64
Q

Neural networks and biology

Describe the topology of a biological neural network.

A

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

65
Q

Neural networks and biology

Describe what’s done because biological connections are metabolically costly to maintain.

A

They are pruned.

66
Q

Neural networks and biology

How do neurons communicate?

A

Via action potentials (AP).

67
Q

Neural networks and biology

How are action potentials generated?

A

By ions travelling across neural membranes.

68
Q

Neural networks and biology

What is generated when ions travel across neural membranes?

A

Action potentials.

69
Q

Neural networks and biology

What do conventional ANNs approximate?

A

Rate coding.

70
Q

Neural networks and biology

Which type of network approximate rate encoding?

A

Conventional ANNs.

71
Q

Neural networks and biology

Describe the leaky-integrate-and-fire (LIF) model. (4)

A

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.

72
Q

Neural networks and biology

What are some “common sense” coding methods for spiking neural networks (SNNs)?

A

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

73
Q

Neural networks and biology

What is STDP short for?

A

Spike-time dependent plasticity

74
Q

Neural networks and biology

What are the ways of training SNNs?

A

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

75
Q

Neural networks and biology

What is neuromorphic hardware?

A

Hardware for running SNNs.

ACIT4610 - Evolutionary AI (11 decks)

Brainscape helps you reach your goals faster, through stronger study habits.
© 2024 Bold Learning Solutions. Terms and Conditions