Brainscape's Knowledge GenomeTM

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


See full index

ACIT4610 - Evolutionary AI > Lecture 08 - Artificial neural networks > Flashcards

Lecture 08 - Artificial neural networks Flashcards

1
Q

Artificial neural networks

What is the name of this function?

A

Step function

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

Artificial neural networks

What is the name of this function?

A

Sigmoid

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

Artificial neural networks

What is the name of this function?

A

Hyperbolic tangent (tanh)

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

Artificial neural networks

What is the name of this simple network?

A

Perceptron

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

Artificial neural networks

What is the name of this function?

A

Rectified Linear Unit (ReLU)

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

Artificial neural networks

What is the name of this function?

A

Leaky ReLU

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

Artificial neural networks

Why are nonlinear activation functions used?

A

Without nonlinear activation functions, the neural network would only be able to model linear functions

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

Artificial neural networks

What is a feed-forward neural network?

A

A network in which each neuron is passed information only one time.

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

Artificial neural networks

What is a fully connected layer?

A

A layer where each neuron is connected to all neurons in the next layer.

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

Artificial neural networks

What is a layer where each neuron is connected to all neurons in the next layer called?

A

A fully connected layer.

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

Artificial neural networks

What is deep learning?

A

Deep learning is the research field that works with deep neural networks

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

Artificial neural networks

What is a deep neural network?

A

Deep neural networks have three or more hidden layers

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

Artificial neural networks

What is the name for a neural network with 3+ layers?

A

Deep neural network

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

Artificial neural networks

What is a recurrent neural network (RNN)?

A

A network where information can pass more than one time to the same neuron.

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

Artificial neural networks

What is a network where information can pass more than one time to the same neuron called?

A

Recurrent neural network (RNN)

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

Artificial neural networks

What does it mean to unfold a recurrent neural network?

A

Diagrams of RNNs are often written in compressed form.

Unfolding means untangling the diagram to show each time step being processed.

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

Artificial neural networks

What is the image an example of?

A

Unfolding a recurrent neural net (RNN)

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

Artificial neural networks

What is a bidirectional RNN?

A

An RNN with an additional layer for input in the reverse order

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

Artificial neural networks

What’s depicted in the image?

A

A bidirectional RNN.

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

Artificial neural networks

What types of data are RNNs good at processing? (SSTV)

A
  • Serial data
  • Sequential data
  • Time-series data
  • Variable-length data
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
21
Q

Artificial neural networks

What are some common applications for RNNS? (TVNS)

A
  • Time-series prediction
  • Video analysis
  • Natural Language Processing (NLP)
  • Speech recognition
22
Q

Artificial neural networks

What is this image an example of?

A

A convolutional layer

23
Q

Artificial neural networks

What is a kernel in an convolutional layer?

A

Tensors that slide across input data, performing calculations on patches of the inputs.

E.g. a 3x3 kernel slides across an image to blur it.

24
Q

Artificial neural networks

What is this called (see image)?

A

Convolution

25
Q

Artificial neural networks

What is this called (see image)?

A

Pooling (Max-pooling)

26
Q

Artificial neural networks

What is max-pooling?

A

Reducing the size of an input tensor by selecting the max value within a window.

27
Q

Artificial neural networks

What are some common applications of convolutional neural networks (CNNs)? (IVG)

A
  • Image classification
  • Video analysis
  • Image generation
28
Q

Artificial neural networks

What is CNN short for?

A

Convolutional neural network

29
Q

Artificial neural networks

What is RNN short for?

A

Recurrent neural network

30
Q

Artificial neural networks

What is an autoencoder?

A

A network with a “bottleneck”

31
Q

Artificial neural networks

What is this an example of?

A

An autoencoder

32
Q

Artificial neural networks

How does an autoencoder work?

A

Autoencoder has a bottleneck that downscales (compresses) an input to its most important representation, then tries to upscale that representation to recreate the original input.

33
Q

Artificial neural networks

What are some common applications for autoencoders? (DCOGS)

A
  • Image denoising
  • Data compression
  • Object detection
  • Image generation
  • Super-resolution
34
Q

Artificial neural networks

What is GAN short for?

A

Generative adversarial network

35
Q

Artificial neural networks

What is the image an example of?

A

A generative adversarial network (GAN)

36
Q

Artificial neural networks

What parts does a GAN consist of? (2)

A
  • The generator
  • The discriminator
37
Q

Artificial neural networks

In a GAN, what does a generator do?

A

It creates data that resembles the real ones

38
Q

Artificial neural networks

In a GAN, what does a discriminator do?

A

It’s a binary classifier which identifies if the data is real or created by the Generator

39
Q

Artificial neural networks

What are some applications of GANs? (1)

A
  • Image generation
40
Q

Artificial neural networks

What is a LIF short for?

A

Leaky-integrate-and-fire

41
Q

Artificial neural networks

What does a leaky integrate-and-fire model do?

A
  • It takes input and integrates (sums) them.
  • The output is usually a 0.
  • If the model has summed past a threshold, the sum is reset (or reduced by some fixed amount) and a 1 is sent as output.
  • The leakiness means the value decays over time.
42
Q

Artificial neural networks

What is the image an example of?

A

A leaky-integrate-and-fire (LIF) neuron.

43
Q

Artificial neural networks

What purpose does the weight in a LIF model have?

A

Weight or synaptic strength defines how much an incoming spike affects the membrane potential or neuron state of the postsynaptic neuron

44
Q

Artificial neural networks

Which two types of neurotransmitters can spiking neurons release?

A

Excitatory and Inhibitory

45
Q

Artificial neural networks

What do Excitatory neurotransmitters do? (2)

A
  • Increases the membrane potential.
  • increases the probability of producing a spike.
46
Q

Artificial neural networks

What do Inhibitory neurotransmitters do? (2)

A
  • Reduces the membrane potential.
  • Reduces the probability of producing a spike.
47
Q

Artificial neural networks

What is a central pattern generator?

A

A generator that produces rhythmic outputs in the absence of rhythmic inputs.

48
Q

Artificial neural networks

What is this image an example of?

A

Outputs from a central pattern generator

49
Q

Artificial neural networks

Who proposed sound localization with spike-coincidence neurons?

A

Jeffress

50
Q

Artificial neural networks

When was sound localization with spike-coincidence neurons proposed?

A

1948

51
Q

What is Sound localization with spike-coincidence neurons?

A

Detecting the location (direction) of incoming sound by producing output spikes when signals arrive at neurons close in time.

ACIT4610 - Evolutionary AI (11 decks)

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