AI-900: How Does a Convolutional Neural Network Work for Image Tasks?

Learn the correct order of steps in a convolutional neural network (CNN) for image classification. Perfect for mastering the AI-900 Microsoft Azure AI Fundamentals exam.

Question

Place the steps of the working of a convolutional neural network (CNN) for an image classification task in the correct order.

Unordered Choices:

• Output Layer Processing
• Feature Extraction
• Neural Network Input
• Flattening Feature Maps
• Training Data Input

Answer

Correct Order:

• Neural Network Input
• Training Data Input
• Flattening Feature Maps
• Output Layer Processing
• Feature Extraction

Explanation

The steps of the working of a convolutional neural network (CNN) for an image classification task are as follows:

1. Training Data Input: Feeding images with known labels (e.g., 0: apple, 1: banana, 2: orange) into the network to train the model.
2. Feature Extraction:Utilizing one or more layers of filters to extract features from each image. Filter kernels begin with randomly assigned weights, generating arrays of numeric values known as feature maps.
3. Flattening Feature Maps:Flattening the feature maps into a single-dimensional array of feature values.
4. Neural Network Input: Feeding the flattened feature values into a fully connected neural network.
5. Output Layer Processing: Processing the output layer of the neural network using a softmax or similar function. This produces a result containing probability values for each possible class, e.g., [0.2, 0.5, 0.3].

Microsoft Azure AI Fundamentals AI-900 certification exam practice question and answer (Q&A) dump with detail explanation and reference available free, helpful to pass the Microsoft Azure AI Fundamentals AI-900 exam and earn Microsoft Azure AI Fundamentals AI-900 certification.