Learn Before
Small Neural Network
A small, or compact, neural network has relatively few hidden units or layers, or relatively few learned parameters, compared with larger networks in the same setting. This label describes the network's architectural size, not its predictive performance.
0
1
Tags
Python Programming Language
Data Science
Machine Learning
Deep Learning
Supervised Learning
Dive into Deep Learning @ D2L
Machine Learning Strategy
Machine Learning Yearning @ DeepLearning.AI
Learn After
Which description best fits a small neural network here?
A network is only considered small if it has few hidden units, few layers, and few parameters at the same time.
Small Neural Network Capacity
Match each network-size clue with what it tells you.
Order the steps for deciding whether a network is small.
Explain why a compact neural network is defined by structure, not by accuracy.
Decide Whether a Model Should Be Called Compact
How is a compact neural network typically described?
What best distinguishes a model’s size from its observed performance?
A Neural Network Can Be Called Small From Its Parameter Count Alone