In [ ]:
from local_utils import *
%pylab inline
If people do not believe that mathematics is simple, it is only because they do not realize how complicated life is.
---John von Neumann
In [7]:
!./rungeogebra
In [ ]:
show_dct_fig()
In [ ]:
img = mpimg.imread('img/abel.jpg'); plt.imshow(img, cmap=mpl.cm.gray);
In [ ]:
show_image(img)
In [ ]:
tiny = img[40:48, 64:72];show_image(tiny)
現代數學的書只分成兩種
那些你讀不完第一行的。
--- C. N. Yang
In [ ]:
tinyDCT = doDCT(tiny);show_image(tinyDCT)
In [ ]:
figure(figsize=(12,36))
for u in range(12):
subplot(6, 2, u+1)
title(str(u))
imshow(dct_all(img, u), cmap=mpl.cm.gray, interpolation="none")
A Neural Algorithm of Artistic Style" by Gatys, Ecker and Bethge. (26 Aug 2015)
http://arxiv.org/abs/1508.06576, http://arxiv.org/abs/1505.07376, http://bethgelab.org/deepneuralart/.
The difference between science and magic is that magicians usually know what they're doing.
-- Ashleigh Brilliant
$\left(\begin{matrix}p(0)\\ p(1)\\ p(-1)\\ p(-2)\\ p(\infty) \end{matrix}\right)=\left(\begin{matrix}0 & 0 & 1\\ 1 & 1 & 1\\ 1 & -1 & 1\\ 4 & -2 & 1\\ 1 & 0 & 0 \end{matrix}\right)\left(\begin{matrix}3\\ 5\\ 2 \end{matrix}\right)$
$\left(\begin{matrix}q(0)\\ q(1)\\ q(-1)\\ q(-2)\\ q(\infty) \end{matrix}\right)=\left(\begin{matrix}0 & 0 & 1\\ 1 & 1 & 1\\ 1 & -1 & 1\\ 4 & -2 & 1\\ 1 & 0 & 0 \end{matrix}\right)\left(\begin{matrix}5\\ 1\\ 6 \end{matrix}\right)$
$\left(\begin{matrix}r(0)\\ r(1)\\ r(-1)\\ r(-2)\\ r(\infty) \end{matrix}\right)=\left(\begin{matrix}p(0)q(0)\\ p(1)q(1)\\ p(-1)q(-1)\\ p(-2)q(-2)\\ p(\infty)q(\infty) \end{matrix}\right).$
$\left(\begin{matrix}r(0)\\ r(1)\\ r(-1)\\ r(-2)\\ r(\infty) \end{matrix}\right)=\left(\begin{matrix}0 & 0 & 0 & 0 & 1\\ 1 & 1 & 1 & 1 & 1\\ 1 & -1 & 1 & -1 & 1\\ 16 & -8 & 4 & -1 & 1\\ 1 & 0 & 0 & 0 & 0 \end{matrix}\right)\left(\begin{matrix}?\\ ?\\ ?\\ ?\\ ? \end{matrix}\right).$
In [ ]:
show_dct_fig()
In [ ]:
w('掌法')
In [ ]:
w('蛤蟆功')-w('歐陽鋒')+ w('洪七公')
In [ ]:
w("華箏")-w("郭靖") + w("周師兄")
In [ ]:
w('丘處機') + (w('鐵杖')-w("柯鎮惡"))
In [ ]:
w("鐵掌") + (w('周伯通')-w("空明拳"))
In [ ]:
w('降龍十八掌')-w("郭靖")
In [ ]:
w("飯")-w("吃")+w("喝")
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
Alec Radford, Luke Metz, Soumith Chintala
Nov 19 2015
