6. DEEP LEARNING ON EDGE Flashcards

15 Questions

1
Q

Which of the following condition is apt for Pruning?

a. The histogram of the weights centered around zeros
b. A bi-modal Gaussian distributed histogram
c. A Poisson distributed histogram
d. None of the above

A

The histogram of the weights centered around zeros

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

Which of the following is a representation of linear symmetric quantization? (x is input, x_int is output, s is scale, z is zero point, b is number of bits

a. x_int = clamp(round(x/s) + z , 0, 2^b – 1)
b. x_int = clamp(round(x/s) + z , -2^b -1, 2^b – 1)
c. x_int = clamp(round(x/s) , 0, 2^b – 1)
d. None of the above

A

c. x_int = clamp(round(x/s) , 0, 2^b – 1)

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

What is a neural network distillation?

a. The learned teacher model is Pruned to form a student model
b. The learned teacher model is Quantized to form a student model
c. Learning a student model with low complexity from a teacher model
d. None of the above

A

Learning a student model with low complexity from a teacher model

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

Pruning of neural networks can be done in which of the following ways

a. Removing some of the weights
b. Reducing the bit-resolution of the weights
c. Reducing the spatial resolution of the input
d. All the possibilities

A

Removing some of the weights

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

Which of the following cases is not useful for pruning of neural networks?

a. A very deep neural network
b. Pruning works in all cases
c. A recursive neural network
d. A modular network with the output of one neural network is input to the next

A

A modular network with the output of one neural network is input to the next

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

How to make rounding error smaller?

a. Decrease q_max
b. Increase q_max
c. Decrease q_min
d. All of the above

A

Decrease q_max

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

How do we find the scale factor and zero point of inputs/activations?

a. Not possible
b. Run representative mini-batches
c. Derive from theory
d. Predict from the trained model

A

Run representative mini-batches

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

What will be the scale factor for a data with minimum value of -50 and maximum value of 150 and for 8-bit resolution.

a. 200
b. 0.7843
c. 0.0039
d. None of the above

A

0.7843

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

What will be the dequantization function for a non-linear quantization (e.g. weight sharing)

a. x’ = s (x_int – z)
b. x’ = s*x_int
c. Needs a look up table (or code book)
d. Not available

A

Needs a look up table (or code book)

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

What will be the starting point for weight sharing by combining Pruning with Quantization?

a. k-Means based clustering of weights
b. Huffman Coding of Weights
c. Quantization of Weights
d. Pruning of Weights

A

k-Means based clustering of weights

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

What will be the typical shape of a histogram after Pruning process?

a. A Poisson distributed histogram
b. A normal distributed histogram
c. A bi-modal Gaussian distributed histogram
d. Any of the above

A

A bi-modal Gaussian distributed histogram

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

Which of the following has the highest complexity of implementation?

a. Symmetric Signed Quantization
b. Symmetric Unsigned Quantization
c. Asymmetric Unsigned Quantization
d. All the above are equal in complexity

A

Asymmetric Unsigned Quantization

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

What will be effective bit size for a quantization with level set {-1, 0, 1}?

a. 3 bits
b. 1.58 bits
c. 1 bit
d. 2 bits

A

1.58 bits

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

Which of the following is useful for implementing a deep neural network on the edge device?

a. Higher number of parameters
b. Neural network weights represented by 32 bit fixed point representation
c. None of the answers
d. Both the higher parameters and 32 bit fixed point representation

A

None of the answers

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

Which of the below case provides the best results?

a. L2 regularization without retrain
b. L1 regularization without retrain
c. L1 regularization with retrain
d. L2 regularization with iterative retraining

A

L2 regularization with iterative retraining

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