-
Irregularity-Aware Graph Fourier Transforms keyboard_arrow_right
This post is the summarization of the paper “Irregularity-Aware Graph Fourier Transforms” by Benjamin Giroult, Antonio Ortega, and Shrikanth S. Narayanan.
-
Code snippets for pytorch keyboard_arrow_right
I am switching to pytorch and here are some piece of code that I think will be useful to copy-paste later.
-
Szemeredi's Regularity Lemma keyboard_arrow_right
Terence Tao revisited the Regularity Lemma.
-
Tensorizing Recurrent Neural Nets keyboard_arrow_right
This post is the summarization of the paper “Wider and Deeper, Cheaper and Faster: Tensorized LSTMs for Sequence Learning” by Zhen He, Shaobing Gao, Liang Xiao, Daxue Liu Hangen He, and David Barber. Published as a conference paper at NIPS 2017, Long Beach, CA, USA.
-
Introducing chalk keyboard_arrow_right
Chalk is a high quality, completely customizable, performant and 100% free blog template for Jekyll.
-
How to configure Chalk keyboard_arrow_right
Learn more about the config file for Chalk and how to set it up properly.
-
Chalk sample post with all elements keyboard_arrow_right
Have a look at all the predesigned elements you can use in Chalk.
-
Deep compression case study - AlexNet keyboard_arrow_right
In this post, we study the result of Song Hans' work on AlexNet.
-
GPU Programming Notes - Part 1 keyboard_arrow_right
May the 4th be with you.
-
Install caffe-GPU on Ubuntu-16.04 keyboard_arrow_right
In this tutorial we install the Caffe version 1.0.0-rc5 from source (check the Makefile for the Caffe version).
-
Finding Lane Lines on the Road keyboard_arrow_right
-
Network Motifs keyboard_arrow_right
This post contains some of my short articles and reading list about network motif and its application.
-
Mini project - Predicting Boston housing price keyboard_arrow_right
Dataset: Boston housing
-
Mini project - Titanic survivors prediction keyboard_arrow_right
Dataset: Titanic survival
-
Principal Component Analysis keyboard_arrow_right
The Principal Component Analysis (PCA) is a technique used in many fields: data science, signal processing, mechanics, etc. As a student of machine learning, I should take sometime to at least review this technique; and maybe ICA too, in some future posts.
- Older posts