ITPEC IP April 2022 Question 91

Neural network — a mathematical model of the network of neurons in the human brain, and the basis of deep learning.

A neural network connects simple units (artificial neurons) in layers. Each unit multiplies its inputs by weights, adds them up and passes the result through an activation function to the next layer. Training adjusts the weights so that the outputs match the training data. Deep learning uses networks with many hidden layers, which learn the features of large volumes of data by themselves.

Answer (c)

Why not others:

• •(a) Content delivery network — delivers web content from cache servers placed near users, spreading the load and speeding up delivery
• •(b) Storage area network — a dedicated high-speed network connecting servers to shared storage devices
• •(d) Ubiquitous network — an environment where anyone can connect anytime, anywhere, with anything

Key rule: Deep learning is machine learning with multilayer neural networks; the other "networks" here are communication infrastructure, not AI models.

Basic Theory · AI-written, may contain errors