Daily Quiz (31.12.2020)

What data would you need to train a voice assistant for a hotel concierge service?

• 2 hours of audio data of people talking to a hotel concierge.

• 10,000 images of hotel concierge activities (check in/out, bellhop, doorman)

• 10 hours of audio data of concierge desk conversations and 50 hours of audio data of the most common guest-concierge interactions with data collected from a studio, from a hotel room, and with sufficient ambient noise.

• 50 hours of hotel lobby video and audio with ambient audio and video data to ensure robustness in different situations.

• You can’t train a model as a voice assistant.

Calculate the F1 score given the following confusion matrix.

• 1.2

• 0.78

• 0.75

• 0.46

Compute the following from the confusion matrix

1. Accuracy

• 87.54

• 92.12

• 91.61

• 90.90

• 91.16

Compute the following from the confusion matrix

2. Sensitivity

• 85.91

• 87.51

• 95.23

• 85.79

• 91.78

Compute the following from the confusion matrix

---> Precision

• 91.86

• 90.90

• 91.87

• 93.42

• 89.97

If you have few data which method you will use?

• Machine Learning

• Auto ML

• Transfer Learning

• Deep Learning

In transfer learning, weights on the earlier layers have to change.

• True

• False

In the case of image classification, later layers identify general patterns in shape and color, such as simple lines and textures, that distinguish different classes of images

• True

• False

In the case of image classification, the first layers in a network are responsible for identifying more complex features such as eyes, ears, and feet.

• True

• False

In Automated ML, which cases are true?

• Robust Enterprise support

• Full control over parameter tuning

• Unlimited use-cases

• Difficult to extend

• Complete customization facility