Currently Migrating into Quarto platform. See the progress on here :)

Posts

  • K-Means Clustering for Imagery Analysis

    In this post, we will use a K-means algorithm to perform image classification. Clustering isn't limited to the consumer information and population sciences, it can be used for imagery analysis as well. Leveraging Scikit-learn and the MNIST dataset, we will investigate the use of K-means clustering for computer vision.

    Oct 26, 2020

  • Text Classification with NLTK

    In this post, we will expand on our NLP foundation and explore different ways to improve our text classification with NLTK and Scikit-learn. In details, we will build SMS spam filters.

    Oct 23, 2020

  • Introduction to Natural Language Processing

    In this post, we will dig into the strong NLP foundation through basic concepts like Tokenization, Stopword handling, Stemming and so on. We will use sklearn with Natural Language ToolKit (NLTK) package, which is widely used in NLP area.

    Oct 22, 2020

  • Image Classification with Cat and Dog

    In this post, we will implement the Image classification (especially on Cat and dog dataset in kaggle) with Convolutional Neural Network using Tensorflow.

    Oct 16, 2020

  • Super-Resolution Convolutional Neural Network

    In this project, it will show CNN model that can enhance the resolution of image using Convolutional Neural Network. The topic is from the paper "Image Super-Resolution Using Deep Convolutional Networks", presented in ECCV 2014.

    Oct 13, 2020

  • CNN with MNIST dataset

    In this post, we will implement various type of CNN for MNIST dataset. In Tensorflow, there are various ways to define CNN model like sequential model, functional model, and sub-class model. We'll simply implement each type and test it.

    Oct 10, 2020

  • CNN Basic

    In this post, We will dig into the basic operation of Convolutional Neural Network, and explain about what each layer look like. And we will simply implement the basic CNN archiecture with tensorflow.

    Oct 7, 2020

  • Causal Graphical Model

    In this post, it will be explained about the causal graphical model. Especially, we will learn about bayesian networks with aspect of conditional independence and its analysis tool "D-separation". Also we will cover bayesian networks with have different characteristics compared to formal bayesian networks. This post is the summary of "Mathematical principles in Machine Learning" offered from UNIST.

    Oct 5, 2020

  • Causal Bayesian Network

    In this post, it will be explained about Granger causality, which is causality in time series data. This post is the summary of "Mathematical principles in Machine Learning" offered from UNIST.

    Oct 2, 2020

  • Causality

    In this post, it will be explained about what the causality is, such as casual graphical model and temporal causality. This post is the summary of "Mathematical principles in Machine Learning" offered from UNIST.

    Oct 1, 2020

  • Training Hello world model for Microcontrollers

    In this post, we'll cover the basic tutorial for training simple regression model with tensorflow lite for for Microcontrollers(TFLM). This post is the summary of youtube video "TinyML Book Screencast - Training the Hello World model", presented by peter warden.

    Sep 24, 2020

  • Image Classification with Fashion MNIST

    In this post, we will implement the Image classification (especially on Fashion MNIST) with Neural Network using Tensorflow.

    Sep 21, 2020

  • Several Tips for Improving Neural Network

    In this post, it will be mentioned about how we can improve the performace of neural network. Especially, we are talking about ReLU activation function, Weight Initialization, Dropout, and Batch Normalization

    Sep 18, 2020

  • XOR Problem in Deep Neural Network

    In this post, it will be mentioned about Basic Concept of Deep Neural Network, and covered XOR problems with Deep Neural Network.

    Sep 16, 2020

  • Regularized likelihood methods

    In this post, it will be explained about Regularized likelihood methods. Usually, two representative methods are introduced, Lasso and Ridge. Moreover, it will cover some other methods that overcome the limitation of Lasso method. This post is the summary of "Mathematical principles in Machine Learning" offered from UNIST.

    Sep 14, 2020