Friday, March 4, 2016

The Basic Concept of TensorFlow

I am preparing to teach TensorFlow in my graduate course. TensorFlow is Google's open software library for machine learning. The first class is about the basic concept of TensorFlow.

Next topic is about "Practice of NNet with the MNIST data."

Tuesday, February 23, 2016

Spoken Language Understanding

One of my research areas is about Dialogues Systems. Nowadays, I am arranging  my work in this research into several ppt files. The following pdf file is the first summary of my work and its topic is Spoken Language Understanding (SLU). Ko).pdf

I will try to post about Dialogue Modeling.

Thursday, February 4, 2016

Multilayer Perceptron

This is my second ppt and Python code for studying Multilayer Perceptron (MLP) and the Back-propagation algorithm. Actually, this will be used in my Artificial Intelligent class.

Please check out the following links.

The next topic is "Introduction of Tensorflow."

Sunday, January 31, 2016


Deep Learning becomes so popular these days, and people who want to study deep learning have to know Python, Perceptron, Multilayer Perceptron (MLP) and the Backpropagation algorithm. So I will make ppt materials including these topics. Actually, this will be used in my Artificial Intelligent class.

Please check out the following links.

This is the first ppt material for Perceptron and a Python code for practice.

And you can start to study Python and Numpy from this: 

The next topic is Multilayer Perceptron.

Wednesday, September 9, 2015

Deep Learning for NLP (Word Embedding)

This is my first presentation for my lecture and talk about Deep Learning. It is focused on Word Embedding. I tried to well organize the contents of word embedding techniques in my presentation.

Wednesday, June 10, 2015

My accepted paper in ACL 2015

My paper related to SLU was accepted in ACL 2015. Its abstract is as follows:

The intelligent personal assistant software such as the Apple’s Siri and Samsung’s S-Voice has been issued these days. This paper introduces a novel Spoken Language Understanding (SLU) module to predict user’s intention for determining system actions of the intelligent personal assistant software. The SLU module usually consists of several connected recognition tasks on a pipeline framework. The proposed SLU module has four recognition tasks including named entity, speech-act, target and operation recognition, and it is developed to simultaneously recognize the four tasks on a recognition framework using Conditional Random Fields (CRF). In the experiments, the new simultaneous recognition method achieves the higher performance of 4% and faster speed of about 25% than other method using pipeline. By a significance test, this improvement is considered to be statistically significant as a p-value of smaller than 0.05.

ACL 2015 will be held in Beijing, China, July 26-31, 2015. I will post the camera-ready version of my paper when it is ready to be published.

Friday, May 15, 2015

topic modeling (LDA)

Before Deep Learning becomes so popular, most researchers had a great interest in topic modeling or LDA. But because LDA requires some knowledge of statistics, many researchers have thought that it is not easy to understand or learn. So I tried to make a ppt material including the fundamental knowledge of both statistics and LDA. Actually, this has been used in my NLP class.

Please check out the following link.

And my next topic is word embedding for NLP as a deep learning technique.