# on 06-Dec-2020 (Sun)

#### Flashcard 6064099167500

Question
The entire training data is denoted as
[default - edit me]

status measured difficulty not learned 37% [default] 0
Lecture 1: Supervised Learning
e or not). Setup Let us formalize the supervised machine learning setup. Our training data comes in pairs of inputs (x,y) ( x , y ) , where x∈Rd x ∈ R d is the input instance and y y its label. <span>The entire training data is denoted as D={(x1,y1),…,(xn,yn)}⊆Rd×C D = { ( x 1 , y 1 ) , … , ( x n , y n ) } ⊆ R d × C where: Rd R d is the d-dimensional feature space xi x i is the input vector of the ith i t h sample yi y i

#### Flashcard 6064101264652

Question
[default - edit me]
D = { ( x 1 , y 1 ) , … , ( x n , y n ) } ⊆ R d × C

status measured difficulty not learned 37% [default] 0
Lecture 1: Supervised Learning
upervised machine learning setup. Our training data comes in pairs of inputs (x,y) ( x , y ) , where x∈Rd x ∈ R d is the input instance and y y its label. The entire training data is denoted as <span>D={(x1,y1),…,(xn,yn)}⊆Rd×C D = { ( x 1 , y 1 ) , … , ( x n , y n ) } ⊆ R d × C where: Rd R d is the d-dimensional feature space xi x i is the input vector of the ith i t h sample yi y i is the label of the ith i

#### Flashcard 6064102313228

Question
Neurons come in all sorts of shapes and sizes