$$ \newcommand{\dint}{\text{d}} \newcommand{\vphi}{\boldsymbol{\phi}} \newcommand{\vpi}{\boldsymbol{\pi}} \newcommand{\vpsi}{\boldsymbol{\psi}} \newcommand{\vomg}{\boldsymbol{\omega}} \newcommand{\vsigma}{\boldsymbol{\sigma}} \newcommand{\vzeta}{\boldsymbol{\zeta}} \renewcommand{\vx}{\mathbf{x}} \renewcommand{\vy}{\mathbf{y}} \renewcommand{\vz}{\mathbf{z}} \renewcommand{\vh}{\mathbf{h}} \renewcommand{\b}{\mathbf} \renewcommand{\vec}{\text{vec}} \newcommand{\vecemph}{\text{\emph{vec}}} \newcommand{\mvn}{\mathcal{MN}} \newcommand{\G}{\mathcal{G}} \newcommand{\M}{\mathcal{M}} \newcommand{\N}{\mathcal{N}} \newcommand{\S}{\mathcal{S}} \newcommand{\diag}[1]{\text{diag}(#1)} \newcommand{\diagemph}[1]{\text{\emph{diag}}(#1)} \newcommand{\tr}[1]{\text{tr}(#1)} \renewcommand{\C}{\mathbb{C}} \renewcommand{\R}{\mathbb{R}} \renewcommand{\E}{\mathbb{E}} \newcommand{\D}{\mathcal{D}} \newcommand{\inner}[1]{\langle #1 \rangle} \newcommand{\innerbig}[1]{\left \langle #1 \right \rangle} \newcommand{\abs}[1]{\lvert #1 \rvert} \newcommand{\norm}[1]{\lVert #1 \rVert} \newcommand{\two}{\text{II}} \newcommand{\GL}{\text{GL}} \newcommand{\Id}{\text{Id}} \newcommand{\grad}[1]{\text{grad} \, #1} \newcommand{\gradat}[2]{\text{grad} \, #1 \, \vert_{#2}} \newcommand{\Hess}[1]{\text{Hess} \, #1} \newcommand{\T}{\text{T}} \newcommand{\dim}[1]{\text{dim} \, #1} \newcommand{\partder}[2]{\frac{\partial #1}{\partial #2}} $$

Generative Adversarial Nets in TensorFlow

Let's try to implement Generative Adversarial Nets (GAN), first introduced by Goodfellow et al, 2014, with TensorFlow. We'll use MNIST data to train the GAN!

The Kebab Bonanza

Turkey = Kebab; Kebab = Turkey

Iran Photo Essay

Iran, one of the mystical lands for world travelers, offers a lot for those who willing to come.

How to Use Specific Image and Description when Sharing Jekyll Post to Facebook

Normally, random subset of pictures and the site's description will be picked when we shared our Jekyll blog post URL to Facebook. This is how to force Facebook to use the specific image and description for our blog post!

Deriving LSTM Gradient for Backpropagation

Deriving neuralnet gradient is an absolutely great exercise to understand backpropagation and computational graph better. In this post we will walk through the process of deriving LSTM net gradient so that we can use it in backpropagation.

Guide to Get Iranian Visa on Arrival

Step by step guide to get Iranian Visa on Arrival at Imam Khomeini Airport, Tehran.

How to Buy Bus Ticket to Yerevan from Tehran

Step by step guide to get a bus ticket to Yerevan, Armenia in Tehran, Iran

Central Hokkaido: Furano, Biei, Asahikawa

Sapporo, the main city of Hokkaido, is a perfect base to explore the central region of Hokkaido Island!

Convnet: Implementing Maxpool Layer with Numpy

Another important building block in convnet is the pooling layer. Nowadays, the most widely used is the max pool layer. Let's dissect its Numpy implementation!

Convnet: Implementing Convolution Layer with Numpy

Convnet is dominating the world of computer vision right now. What make it special of course the convolution layer, hence the name. Let's study it further by implementing it from scratch using Numpy!