JDA-Azure-Module 2-Models

What is the name of the Microsoft model that is trained with huge volumes of captioned images from the Internet and includes both a language encoder and an image encoder?

• Florence

• Leonardo

• Picasso

• Vincent

What type of neural network architecture is commonly used for computer vision tasks such as image classification and object detection?

• Recurrent neural network (RNN)

• 
  Convolutional neural network (CNN)

• Transformer

• Autoencoder

Identifying to which category an image belongs

• Tagging

• Captioning

• Object detection

• Image classification

Locating individual objects within an image

• Tagging

• Captioning

• Object detection

• Image classification

Generating appropriate descriptions of images

• Tagging

• Captioning

• Object detection

• Image classification

Compiling a list of relevant text tags for an image based on its content

• Tagging

• Captioning

• Object detection

• Image classification

CNNs start with randomly assigned filter weights and then adjust them during the training process to reduce the loss

• True

• False

Transformers are only used for natural language processing tasks, not for computer vision tasks.

• True

• False

You need to create a separate resource for each Azure AI service you want to use

• True

• False

We cannot use Azure AI Vision to train a custom model for image classification or object detection.

• True

• False