問19
頻出度★★☆
ディープラーニングを構成する技術の一つであり，人間の脳内にある神経回路を数学的なモデルで表現したものはどれか。
令和2年度 ITパスポート試験 問19
テクノロジ系基礎理論 › 情報に関する理論
This question's explanation and your answers so far.
解説
問 19
Incorrectア
A Content Delivery Network (CDN) is a distribution infrastructure mechanism that spreads Web content across delivery servers close to users so that it can be delivered quickly and reliably. It has nothing to do with the brain’s neural circuits or with machine learning.
Incorrectイ
A Storage Area Network (SAN) is a method of connecting servers and storage devices over a dedicated high-speed network. It is a technology for storing and sharing data, not a technology that makes up deep learning.
- ウ
正解 The correct answer is ウ “Neural Network”. A neural network is a mechanism that uses a mathematical model to imitate the workings of the nerve cells (neurons) in the human brain and the neural circuits that connect them; it has a structure that weights inputs and passes them to the next layer. Stacking many of these layers to raise expressive power is deep learning, and a neural network is precisely the core technology that makes up deep learning. It therefore fully matches the description in the question.
Incorrectエ
A ubiquitous network refers to the concept of an environment in which one can connect to the network “anytime, anywhere”. It is an idea about a form of network usage, not a mathematical model that represents the brain’s neural circuits.
ここがポイント
- A neural network is a mechanism that imitates the brain’s neurons and neural circuits with a mathematical model; stacking its layers deeply yields deep learning.
- Distinguish the confusable “~ network” terms (CDN, SAN, ubiquitous) — they are all technologies related to communication, storage, or usage form, and belong to a different domain from AI / machine learning.
用語