# CNN as N Gram Detector

CNN has been used intensively in image processing tasks. However, what about in text? is it feasible to use it in text? and what kind of output will it be translated when we’re using CNN in text?

Tags:

CNN has been used intensively in image processing tasks. However, what about in text? is it feasible to use it in text? and what kind of output will it be translated when we’re using CNN in text?

Tags:

**BLEU** is a metric to quantify effectiveness of an Machine Translation (MT). It stands for **B**i**L**ingual **E**valuation **U**nderstudy $^{[1]}$. In general it solves the problem of different human translation **references** by different annotators when comparing to machine generated **translation**. Let’s start from using BLEU in NLTK translation package $^{[2]}$

Tags:

Tags:

This is my personal choice for productivity tools, you may find these tools usefull but you may also find differently. I use ubuntu desktop and android phone, so my personal choices will based on these platforms.

Tags:

graph LR
subgraph input layer
X1[x1]
X2[x2]
X3[x3]
end
subgraph hidden layer
H1((h1))
H2((h2))
H3((h3))
end
subgraph output layer
YHAT((yhat))
end
X1 --> H1
X1 --> H2
X1 --> H3
X2 --> H1
X2 --> H2
X2 --> H3
X3 --> H1
X3 --> H2
X3 --> H3
H1 --> YHAT((yhat))
H2 --> YHAT
H3 --> YHAT

Tags:

Short introduction to vector operation in python numpy in logistic regression.

Tags:

This is my notes for Deep Learning Course in Coursera. I jumped straight to week 2 because week 1 is about introduction that I’ve known. Week 2 in summary is structured as: starting from binary classification with logistic regression, loss function and cost function, computational graph.

Tags:

This is a too long didn’t listen (TLDL) version of radical candor ep.5 summary. As a reminder for myself in the future and a person who prefer reading than listening because I quickly forgot. NB: when I use “people” here it usually means software engineers.

Tags:

A general advice on focusing on positive thoughts and less on negative thoughts. I found this will very helpful for me for now and in the future to fight for my thoughts and focus on what’s important. Hopefully this could also be inspiration for anyone else. Special thanks for Talk at Google and Happify to share.

Tags:

This post shows how to do conjoint analysis using python. Conjoint analysis is a method to find the most prefered settings of a product [11].

Tags:

In this post, I just want to summarize statistics terms, that might be used when analyzing data or reading papers.

Tags:

I’ve implemented virtebi algorithm and explain the advantage from naive approach at last post. Now it’s time to look at another use case example: the Part of Speech Tagging!

Tags:

Introduction to Virtebi Algorithm, Virtebi Path, Markov Chain, Hidden Markov Model.

Tags:

One way ANOVA (Analysis of Variance) is a technique for hypothesis testing. It is used to test whether the means of different group is really different.

Tags:

It is a probabilistic data structure, that is commonly used to ask question “whether an element is in it or not?”. From my description, it does seems like a job that Set can do, sooo…

Tags:

moved from here

Tags: