Coursera Flashcards
machine learning (older definition)
the science of getting computers to learn, without being explicitly programmed
supervised learning
given a data set and already know what our correct output should look like, having the idea that there is a relationship between the input and the output
regression problem
trying to predict results within a continuous output, meaning that we are trying to map input variables to some continuous function (eg house price based on square feet)
classification problem
trying to predict results in a discrete output (eg breast tumor is malignant or benign)
unsupervised learning
allows us to approach problems with little or no idea what our results should look like
clustering algorithm
eg. Take a collection of 1000 essays written on the US Economy, and find a way to automatically group these essays into a small number that are somehow similar or related by different variables, such as word frequency, sentence length, page count, and so on.
machine learning (modern definition)
A computer program is said to learn from experience E with respect to some class of tasks T and performance measure P, if its performance at tasks in T, as measured by P, improves with experience E.
cost function
This function is otherwise called the “Squared error function”, or Mean squared error.
gradient descent equation
course notation
m: number of training examples x’s = “input” variable/features y’s = “output” variable/”target” variable
gradient descent for linear regression equation
matrix
rectangular array of numbers written between square brackets; in other words a 2-D or 2-dimensional array
dimension of a matrix
The number of rows in a matrix X the number of columns in a matrix.
If A is a matrix, what is Aij referring to?
The entry in the ith row and jth column
vector
A vector is an n x 1 matrix; in other words it is a special case of a matrix where there is only 1 column
If y is a vector, what is yi referring to?
The entry in the ith row. Note that there are two ways of indexing vectors, starting at 1 (the more common in math) or starting at 0 (used in some applications for machine learning).
scalar multiplication (matrix)
Multiplying a matrix by a number.
Is matrix multiplication commutative?
No
Is matrix multiplication associative?
Yes
What is the identity matrix?
Denoted by I or Inxn
For any matrix A, A • I = I • A = A
What is a matrix that does not have an inverse called?
Singular or degenerate
matrix inverse operation
tbd
matrix transpose
ATij = Aji
xj(i)
value of feature j in the ith training example
