Showing posts from 2017

Build Knowledge Graph from unstructured corpus using Machine Learning

Problem of creating knowledge graph from unstructured data is a well known machine learning problem. Not even a single org has achieved 100% accuracy for completely enriched knowledge graph . I have few findings that will help to kick-start for a person who is new in to this .

Before move to findings , i will let you to walk through the problem of building knowledge graph from unstructured corpus . Lets consider this scenario . Suppose we have very small corpus :

"Apple was founded by Steve jobs and current CEO is Tim Cook. Apple launched several products like Ipad, iphone , MAC etc. "

Corpus may be very complex sentences also . Problem is how can we build a knowledge graph out of this unstructured corpses . If we create generic knowledge graph , then our system should be able to provide answers like "who founded Apple ?" , " What are products launched by Apple ?" etc .

Few techniques to create knowledge graph :

1.) Supervised Technique :
Supervised models use…

Getting started with Tensorflow , keras and theano - Development setup with Anaconda Installation

Below are the steps to setup your development environment  for Deep learning :
1.) Download and Install Anaconda from here :
2.) Create a conda environment for data science development so that it doesn't affect the other install components .
conda create -n tensor_keras_py2.7 python=2.7 pandas scikit-learn jupyter matplotlib
3.) Activate the created environment
source activate tensor_keras_py2.7 4.) Install tensorflow inside activated env. pip install tensorflow 5.) Install keras inside activated env.    pip install keras 6.) Install opencv inside activated env.    pip install opencv-python

Test your environment
1.) Type ipython in the shell , which should open ipython console . 2.) Type import tensorflow,keras  , it should reply using tensorflow backend 

Switching keras backend from Tensorflow to theano keras backend is set in a hidden file stored in your home path . You can find it at $/.keras/keras.json . You can open it with a text editor and you sh…

Getting started with Deep Learning Caffe Framework - Fastest way(Installation +Web Demo)

Here is the fastest way to get started with caffe deep learning framework with installation and basic we application demo for image classification :

Installation : Here i am using caffe official ubuntu image and running it on docker . Follow the steps mentioned below :
1.) Install docker setup on your machine . Follow this link :
2.) I have build caffe ubuntu image and push to docker hub . You can pull it in to your local.
docker pull anishratnawat/caffe_deep_learning
3.)Run this command on terminal :
docker run -ti -p 5000 anishratnawat/caffe_deep_learning bash  
 // it will download the image if its not downloaded before.
// When downloading finishes , terminal will enter in to image bash and your terminal will change to :
If you install any necessary packages inside that image then you need to commit it to make changes persist .
docker commit <ContainerId> <NewImageName>