Object Recognition has recently become one of the most exciting fields in computer vision and AI. The ability of immediately recognizing all the objects in a scene seems to be no longer a secret of evolution. With the development of Convolutional Neural Network architectures, backed by big training data and advanced computing technology, a computer now can surpass human performance in object recognition task under some specific settings, such as face recognition.

The receptive field is perhaps one of the most important concepts in Convolutional Neural Networks (CNNs) that deserves more attention from the literature. All of the state-of-the-art object recognition methods design their model architectures around this idea. However, to my best knowledge, currently there is no complete guide on how to calculate and visualize the receptive field information of a CNN

My daily work usually starts by opening an SSH connection to a server, running a docker image (with RStudio Server or Jupyter on it), and analyzing data or programming directly on the browser. It was always convenient like that until I got sudden disconnection last month. Suddenly anything stops working,

Setting up a development environment that is deployable has always been a complicated task for data scientists. In my case, I have a bunch of environments, each designed for different purposes. For example, I use R for time-series forecasting and descriptive statistics, while using Python (with Scikit-Learn, Tensorflow, and sometimes Caffe) for deep learning and reinforcement learning. It is almost impossible for me to have one environment for every purpose.

It has been very long time ago since I decided that I need to have a personal blog. But my procrastination power was so high that I could not manage to do so earlier. And now, since my Ph.D. is moving slowly to its end, the need to have an updated detail CV in the form of a blog has finally created enough kick-ass force.