Restricted Boltzmann Machine, a complete analysis. Part 3: Contrastive Divergence algorithm

Deeplearning.ai: CNN week 1 — Convolutional Neural Network terminology

From edge filtering to…

Restricted Boltzmann Machine, a complete analysis. Part 1: introduction & model formulation

Someday ago, my colleague asked me about RBM algorithm and what is the difference vs other learning algorithms. It is really interesting about this algorithm as Netflix used…

SuperResolution by Unet and customized feature loss

Unet is one of the universal deep learning…

Getting started with Torch and Lua language

Introduction: Torch is a scientific computing framework which is based on LuaJIT (Lua just in-time compiler) and of we will code in Lua language.

Particularly, Torch is more favorable in the research community as readable source…

Deeplearning.ai CNN week 3: Object detection

Heading to the YOLO algorithm

• Classification vs Localization vs Dectection?

Installing multiple CUDA + cuDNN versions in the same machine for Tensorflow and Pytorch

Restricted Boltzmann Machine, a complete analysis. Part 2: A Markov Random Field model

This second post of the Restricted Boltzmann Machine is to explain about its core properties and establish fundamental tools/knowledge to solve it. We will see these things:

Deeplearning.ai: CNN Week 2 — Convolutional Neural Network Architecture

Case studies of CNN

Tensorflow — day 1+2: High level APIs

After 2 days of starting to touch the Tensorflow framework. I am starting to write my experience recap. Of course, it follows the tutorial of tensorlow but I try to make figures and important points for new comers as me (simple/easier to understand).