Skip to main content

Back to the full dot-point answer

SingaporeComputer ScienceQuick questions

Machine Learning and Emerging Technologies

Quick questions on Neural networks and deep learning explained: H2 Computing

7short Q&A pairs drawn directly from our worked dot-point answer. For full context and worked exam questions, read the parent dot-point page.

What is the artificial neuron?
Show answer
The building block is an artificial neuron. It takes several inputs xix_i, each with a weight wiw_i, computes a weighted sum, adds a bias bb, and applies an activation function ff:
What are layers?
Show answer
Neurons are organised into layers:
What are the role of the weights?
Show answer
The weights are the network's adjustable parameters. Each weight sets the strength and importance of one connection - how much an input influences a neuron. The pattern of weights is what the network "knows"; finding good weights is the whole goal of learning.
What is deep learning?
Show answer
Deep learning uses neural networks with many hidden layers (deep networks). Each layer can learn increasingly abstract features automatically from raw data - early layers detect edges, later layers detect shapes, then objects. This makes deep learning excel at perception tasks such as image recognition, speech recognition and natural language processing, given large datasets and computing power.
What is q1?
Show answer
Name the three kinds of layer in a feedforward neural network. [1 mark]
What is q2?
Show answer
How does a single neuron compute its output? [2 marks]
What is q3?
Show answer
In one sentence, how is a neural network trained? [2 marks]

Have a question we have not covered?

This dot-point answer is short enough that we have not extracted many short questions yet. Read the full dot-point answer or ask Mo, our study assistant, in the chat for follow ups.

All Computer ScienceQ&A pages