Edge Computing

Question 1

What are considerations when deploying edge computing systems? (Select all that apply)

Memory constraints

Processing power limitations

Centralized data storage

Energy efficiency

Answer 1

Memory constraints
Processing power limitations
Energy efficiency

Question 2

Which of the following is an example of quantization in TinyML?

Using efficient neural network architectures

Removing unnecessary neurons in a model

Reducing the precision of numbers to decrease model size

Training a smaller model to mimic a larger model

Answer 2

Reducing the precision of numbers to decrease model size

Question 3

Which of the following are benefits of edge computing? (Select all that apply)

Improved data privacy

Higher dependency on cloud servers

Reduced bandwidth usage

Reduced latency

Answer 3

Improved data privacy
Reduced bandwidth usage
Reduced latency

Question 4

Machine learning algorithms use statistics to find patterns in massive amounts of data.
True
False

Answer 4

True

Question 5

Which of the following statement is FALSE for TinyML?

Reducing parameters

Targeting battery-powered microcontrollers

Focus on training, not inferencing

Hardware optimized paths

Answer 5

Focus on training, not inferencing

Question 6

Which is the hardest stage in deploying machine learning on the edge?

Running inference on the edge

Sample Sensor data

Training the model

Sending data to the cloud

Answer 6

Running inference on the edge