본문 바로가기

AI Tech - Naver Boostcamp/1. Python & AI Math3

3. Gradient Descent (Basic) 3. Gradient Descent (Basic) Created: August 4, 2021 10:05 AM Reviewed: No Differentiation $$f&#39;(x) = \lim\limits_{h\to0} {f(x+h)-f(x)\over h}$$ Numpy: sympy.diff import sympy as sym from sympy.abc import x sym.diff(sym.poly(x**2 + 2*x + 3), x) # Differenciate by xPoly(2*x + 2, x, domain = &#39;zz&#39;) Gradient ascent $$x&#39; = x+f&#39;(x)$$ 1) f&#39;(x) < 0 x&#39; = x + f&#39;(x) < x 2) f&#.. 2021. 8. 9.
2. What is matrix? Matrix - definition maxtrix: 2-dimensional array which has vector-elements.In Numpy, 'row vector' is a unit.matrix = 행렬 = 벡터를 원소로 가지는 2차원 배열Numpy에서는 행(row)이 기본 단위임. X=(xij)\bm X = (x_{ij})X=(xij​)In linear algebra, the transpose of a matrix is an operator which flips a matrix over its diagonal; that is, it switches the row and column indices of the matrix A by producing another matrixXT=(xji)\bm.. 2021. 8. 9.
1. What is vector? 1. What is Vector? Created: August 3, 2021 10:56 AM Reviewed: No Hadamard product (= elementwise product = 성분곱) $$\bm x = [x_1, x_2, ... , x_d]$$ $$\bm y = [y_1, y_2, ... y_d]$$ $$\bm x \odot \bm y = [ x_1y_1, x_2y_2, ... x_dy_d ] $$ In Numpy, elementwise product equals ***** norm norm is equal to the distance from the origin (0, 0). 1) $L_1-norm$ $$L_1-norm = ||\bm x||_1 = \sum_{\substack{i=1}}.. 2021. 8. 3.

티스토리툴바