supriya-gdptl

pip show tensorflow
pip uninstall tensorflow

# Tensorflow 1.4 works only with Python 3.5
# to install downgrade Python 3.6 to Python 3.5 in Anaconda
conda install python=3.5
# now install tensorflow 1.4
sudo apt-get install python3-pip python3-dev
pip install tensorflow

supriya-gdptl

# To generate synthetic graphs with communitites and finding these communitites uing Girvan-Newman algorithm
'''
installation steps:
 1) pip install networkx
 2) pip install python-louvain
 3) pip install community
'''
import networkx as nx
import matplotlib.pyplot as plt
%matplotlib inline

supriya-gdptl

Links to blogs that explain how attention mechanism works in Computer Vision and Natural Language Processing tasks.

1. Attention Mechanism by Heuritech Le Blog

2. Visual Attention Model in Deep Learning by Tristan

3. Attention and Menory in Deep LEarning and NLP: wildml post by Denny Britz

4. Attention in Convolutional Neural Nets by Dan Vatterott

supriya-gdptl

To add Latex code in HTML website, there are two ways,

1. Simple way to add Latex code is using HTML image tag(for more info visit codecogs):

<img src="http://latex.codecogs.com/gif.latex?1+sin(x)" border="0"/>

2. Using MathJax CDN:

supriya-gdptl

1. Inductive Bias : It is a set of assumptions learner uses to predict results for unseen inputs. Every machine learning algorithm that is trained for generalization purpose has inductive bias. For example, linear regression model assumes that output Y is linearly dependent on input X. This introduces bias in the training called inductive bias. Similarly for SVM, inductive bias is: the classes are separated by large margin. Please refer to website for knowing inductive biases of other machine learning algorithms.

2. Self Organizing Maps :

• Self organizing maps(SOM) are special type of neural network used for unsupervised feature learning. SOM falls into the category of non-linear dimensionality reduction methods.

• Unlike normal neural network that apply error-correcting learning algorithm(e.g. backpropagation with gradient descent), SOM apply competitive learning algorithms.

• It maps mul

supriya-gdptl

- ![#f03c15](https://placehold.it/15/f03c15/000000?text=+) `#f03c15`
- ![#c5f015](https://placehold.it/15/c5f015/000000?text=+) `#c5f015`
- ![#1589F0](https://placehold.it/15/1589F0/000000?text=+) `#1589F0`

1st generates red block
2st generates green block
3st generates blue block

supriya-gdptl

To install CUDA9.0 and cuDNN 7.0, follwo instruction given on following website:
https://medium.com/@zhanwenchen/install-cuda-and-cudnn-for-tensorflow-gpu-on-ubuntu-79306e4ac04e
-----

To install anaconda on new machine:
(To install perticular version of anaconda refer https://repo.continuum.io/archive/)

wget https://repo.continuum.io/archive/Anaconda3-5.1.0-Linux-x86_64.sh
bash Anaconda3-5.1.0-Linux-x86_64.sh

supriya-gdptl

ps u pid_number  ->To see the owner of process 'pid_number'

screen -S [any_name] ->put code for running

Ctrl A D -> to detach the screen

screen -r [same_above_name] -> to resume screen

go to screen and type exit -> to terminate the screen
OR

supriya-gdptl

sudo apt-get update
sudo apt-get install firefox

supriya-gdptl

Include package:

\documentclass{article}
\usepackage{natbib}
  
Options for the \cite command and their outputs:

\citet{key}	Jones et al. (1990)
\citet*{key}	Jones, Baker, and Smith (1990)
\citep{key}	(Jones et al. 1990)