3
1

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?

More than 5 years have passed since last update.

【Chapter 2.2】文系大学生が読み解くDeep Learning Book

Posted at

【Chapter 2.2】文系大学生が読み解くDeep Learning Book

概要

数学的素養がほとんど高校生止まりの
とある文系大学生が著名なDeep Learning Book
を読み解いていきたいと思います。(=翻訳・まとめ・解釈)

Chapter 2.2 Multiplying Matrices and Vectors / 行列とベクトルの掛け算

行列演算

行列演算(行列と行列の掛け算)

を行うためには、

Aの形が $i \times k$

Bの形が $k \times j$

でなければなりません。

$$
C_{i,j} = \Sigma_{k} A_{i,k}B_{k,j}
$$

Element-wise Product / Hadamard Product / アダマール積

行列の成分ごとの積 = Element-wise Product を、

$$
A \odot B
$$

Dot Product / 内積 / ドット積

行列やベクトル同士の積 = Dot Product を、

$$
\mathbf {x} ^{\mathsf {T}}\mathbf {y}
$$

とTのような表記をします。

その他の行列演算に関する公式

$$
A(B+C) = AB + AC
$$

$$
A(BC) = (AB)C
$$

$$
\mathbf {x} ^{\mathsf {T}}\mathbf {y}
= \mathbf {y} ^{\mathsf {T}}\mathbf {x}
$$

$$
(\mathbf {AB}) ^{\mathsf {T}} =
\mathbf {B} ^{\mathsf {T}}
\mathbf {A} ^{\mathsf {T}}
$$

$$
\mathbf {x} ^{\mathsf {T}}\mathbf {y}
= (\mathbf {x} ^{\mathsf {T}}\mathbf {y})\mathsf {T}
= \mathbf {y} ^{\mathsf {T}}\mathbf {x}
$$

単位行列

$$
A_{m,1}x_{1} + A_{m,2}x_{2} + ... + A_{m,n}x_{n} = b_{m}
$$

の時、

単位行列$I$は、

$$
I=
\begin{pmatrix}
1 & 0 & 0 \\
0 & 0 & 1 \\
0 & 0 & 1
\end{pmatrix}
$$

最後に

間違いやご指摘などが御座いましたらご教示願います!

参考文献

3
1
0

Register as a new user and use Qiita more conveniently

  1. You get articles that match your needs
  2. You can efficiently read back useful information
  3. You can use dark theme
What you can do with signing up
3
1

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?