features.adoc
= AsciiDoc Example
:date: 2020-02-21 16:38:20
:toc_run: true
:publications_src: content/pages/zotero_single.bib
:status: hidden
:stem: latexmath
== Links
http://asciidoc.org/userguide.html[AsciiDoc Homepage]
== Table (Playing with Kaggle; uses AsciiDoc includes)
--- snip ---
include::../includes/ffe/table.adoc[]
--- snap ---
(1) augmented: one additional variant per image rotated randomly in [-5,5] degree. +
(2) bn: batch-norm
== Mathematics
_Inline Math:_ stem:[f_{i}(x) = \int_{\tau(\pi)}^\infty e(x,y)dy]
_Display Math:_
[stem]
++++
\begin{bmatrix}
a_{11} & a_{12} & \dots \\
\vdots & \ddots & \\
a_{n1} & & a_{nn}
\end{bmatrix}
++++
_Inline Math:_ stem:[(\Omega,\mathcal{F},P) \coloneqq (\Omega^+ \times \Omega^-,\mathcal{F^+ }\otimes\mathcal{F^- },P^+ \times P^- )]
_Display Math:_
The Wiener process in stem:[(\Omega,\mathcal{F},P)] is defined by
[stem]
++++
\omega(t) \coloneqq
\left\{
\begin{array}{cc}
(\omega^+(t),0) & t\geq 0 \\
(0,\omega^-(t)) & t<0
\end{array}
\right.
++++
More math...
[stem]
++++
\tag {3.1a}
\begin{aligned}
dy_t &= \sum_{i=1}^n \frac{x_t^i}{\|x_t\|^2} \left( \sum_{j=1}^n
u_{ij} x_t^i\,dt + \sum_{k=1}^m \sum_{j=1}^n v_{ij}^k
x_t^j\circ dW_t^k\right) + \cdots\\
\cdots &+ \frac{1}{2} \sum_{i,j}^n \left( \frac{\delta_{ij}}{\|x_t\|^2} -
\frac{2x_t^i x_t^j}{\|x_t\|^4} \right)\; \sum_k^m \sum_{l,p}^n
v_{il}^k v_{jp}^k\, x_t^l x_t^p\;dt
\end{aligned}
++++
With stem:[z_t \coloneqq \frac{x_t}{\|x_t\|}] we get the following differential equation on the unit sphere:
[stem]
++++
\tag{3.1b}
\begin{aligned}
y_t &= y_0 + \int_0^t z_t^TUz_t- \|z_t\|^{-2}
z_t^T\hat{V}\hat{V}^T z_t + \frac{1}{2}\text{ trace
}(\hat{V}\hat{V}^T)\,dt +\cdots\\
\cdots &+ \sum_{k=1}^m \int_0^t z_t^TV^kz_t\circ dW_t^k
\end{aligned}
++++
=== Outline as partial TeX file inclusion
Line block - takes only the inner part of a LaTeX display-math environment by specifying row delimiters for the included LaTeX file:
--- snip ---
[stem]
++++
include::../includes/ffe/formulas.tex [lines=6..12]
++++
--- snap ---
Single line (as inline): start include -> stem:[
include::../includes/ffe/formulas.tex [lines=16]
] <- stop include
== Footnotes
Footnotes are possible, like using footnote:[First footnote] and footnote:[Second footnote].
== Citations
- Cited text 1: [@@touchetteBasicIntroductionLarge2012]
- Cited text 2 footnote:[Interesting in terms of content, by the way]: [@dematteisRogueWavesLarge2018]
== SVG image
// Disable all captions for figures here ('Figure 1' prefix). But in general AsciiDoc
// seems to be the most versatile format for images and figures
:!figure-caption:
[.left.text-center]
image::{static}/images/neuron.svg[title="Caption (Neuron image - 50%)", width=50%]
== Code
=== Verbatim file inclusion
[source]
----
include::../includes/ffe/features.py[]
----
=== Normal code block
....
from torch.utils.data import TensorDataset
from torch import Tensor, LongTensor, FloatTensor
def loadData(path) -> Tuple[np.ndarray, np.ndarray]:
'''
Load data from kaggle mnist set.
path -- input csv
Return scaled images [0,1] and labels (if available)
as numpy arrays (dtype: float32, int64)
'''
# Read
df = pd.read_csv(str(path)) # 40.000 entries
# tdata = pd.read_csv(data_raw_dir + sep + 'train.csv') # 28.000 entries
has_labels = True if 'label' in df.columns else False
....
Some `inline code`.
table.adoc
[width="100%]
|=======
| Model | Epochs | bs | lr | Momentum | Result (local) | Result (Kaggle) | Remarks
| SimpleNet | 50 | 20 | 0.007 | 0.9 | ~97 | |
| ConvNet | 50 | 25 | 0.008 | 0.9 | | 99.257 |
| " | 50 | 17 | 0.008 | 0.9 | 99.1964 | | augmented
| " | 50 | 17 | 0.008 | 0.9 | 99.3143 | 99.342 | augmented bn
| Binary Ensemble | 25 | 17 | 0.007 | 0.9 | >99 | |
| " | 22 | 17 | 0.0085 | 0.9 | 99.23928 | 99.328 | augmented
| " | 22 | 17 | 0.0085 | 0.9 | 99.34643 | 99.357 | augmented bn
|=======