RoboTech

How Many Types Are There For Neural Network Architecture?

"Neural Network Zoo" Chart

REFERENCE:

Van Veen, F. & Leijnen, S. (2019). The Neural Network Zoo.

https://www.asimovinstitute.org/neural-network-zoo/

A neural network is actually just a mathematical function. You enter a vector of values, those values get multiplied by other values, and a value or vector of values is output.

They are very useful in problem domains where there is no known function for approximating the given features (or inputs) to their outputs (classification or regression). One example would be the weather - there are lots of features to the weather - type, temperature, movement, cloud cover, past events, etc - but nobody can say exactly how to calculate what the weather will be 2 days from now. A neural network is a function that is structured in a way that makes it easy to alter its parameters to approximate weather predication based on features.

Therefore, Neural Network is a function and has a structure suited to "learning". One would take the past five years of weather data - complete with the features of the weather and the condition of the weather 2 days in the future, for every day in the past five years. The network weights (multiplying factors which reside in the edges) are generated randomly, and the data is run through. For each prediction, the NN will output values that are incorrect.

Using a learning algorithm based in calculus, such as back-propagation, one can use the output error values to update all the weights in the network. After enough runs through the data, the error levels will reach some lowest point. The goal is to stop the learning algorithm when error levels are at a best point. The network is then fixed and at this point it is just a mathematical function that maps input values into output values just like any old equation.

REFERENCE:

https://softwareengineering.stackexchange.com/questions/72093/what-is-a-neural-network-in-simple-words

A:
Two types of techniques have been used in the literature for semantic orientation-based approach for sentiment analysis, viz., (i) corpus based and (ii) dictionary or lexicon or knowledge based.

In this chapter, we explore the corpus-based semantic orientation approach for sentiment analysis.

Corpus-based semantic orientation approach requires large dataset to detect the polarity of the terms and therefore the sentiment of the text.

The main problem with this approach is that it relies on the polarity of the terms that have appeared in the training corpus since polarity is computed for the terms that are in the corpus.

This approach has been explored well in the literature due to the simplicity of this approach [29, 120].

This approach initially mines sentiment-bearing terms from the unstructured text and further computes the polarity of the terms.

Most of the sentiment-bearing terms are multi-word features unlike bag-of-words, e.g., “good movie,” “nice cinematography,” “nice actors,” etc.

Performance of semantic orientation-based approach has been limited in the literature due to inadequate coverage of the multi-word features.

Agarwal, B., & Mittal, N. (2016). Semantic Orientation-Based Approach for Sentiment Analysis.

Sentiment Analysis, Multi-word Features, Semantic Orientation, Seed Word List, Mutual Information Method

P:
https://link.springer.com/chapter/10.1007/978-3-319-25343-5_6

https://www.semanticscholar.org/paper/Semantic-Orientation-Based-Approach-for-Sentiment-Agarwal-Mittal/d8d0d92dd282911c7e00361926f2d352a2e03b01

https://www.researchgate.net/publication/301265951_Semantic_Orientation-Based_Approach_for_Sentiment_Analysis

https://app.razzi.my/findgref?gid=1sICPEHZfxAmrC9Xse2vjyKQ7-vImSElF

JSHint, A Static Code Analysis Tool for JavaScript

The project aims to help JavaScript developers write complex programs without worrying about typos and language gotchas.

Any code base eventually becomes huge at some point, so simple mistakes — that would not show themselves when written — can become show stoppers and add extra hours of debugging. So, static code analysis tools come into play and help developers spot such problems. JSHint scans a program written in JavaScript and reports about commonly made mistakes and potential bugs. The potential problem could be a syntax error, a bug due to an implicit type conversion, a leaking variable, or something else entirely.

Only 15% of all programs linted on jshint.com pass the JSHint checks. In all other cases, JSHint finds some red flags that could've been bugs or potential problems.

Please note, that while static code analysis tools can spot many different kind of mistakes, it can't detect if your program is correct, fast or has memory leaks. You should always combine tools like JSHint with unit and functional tests as well as with code reviews.

https://jshint.com/

ABSTRACT:

This research is intended to give detailed overview of basic concept of two text mining techniques namely information retrieval and information extraction.

This paper has provided a comparison table of both these techniques on the basis of characteristic and their relationship to each other.

We have also underlined many interesting research challenges which will benefit in managing the extracted valuable information.

Later this research has also been motivated to highlight the main role of information extraction in terms of retrieval context in future to be played.

KEYWORD:

Information retrieval, Information extraction, Text mining

CITE:

Ahmad, P.H., & Dang, S. (2014). A Comparative Study on Text mining Techniques.

PUBLINK:

http://www.gjar.org/articles/A-Comparative-Study-on-Text-mining-Techniques

DOCLINK:

https://www.ijsr.net/archive/v3i12/U1VCMTQ4NjU=.pdf

RGTLINK:

https://www.researchgate.net/publication/270704468_A_Comparative_Study_on_Text_mining_Techniques

While many lexica annotated with words polarity are available for sentiment analysis, very few tackle the harder task of emotion analysis and are usually quite limited in coverage.

In this paper, we present a novel approach for extracting - in a totally automated way - a high-coverage and high-precision lexicon of roughly 37 thousand terms annotated with emotion scores, called DepecheMood.

Our approach exploits in an original way 'crowd-sourced' affective annotation implicitly provided by readers of news articles from rappler.com.

By providing new state-of-the-art performances in unsupervised settings for regression and classification tasks, even using a na\"{\i}ve approach, our experiments show the beneficial impact of harvesting social media data for affective lexicon building.

approach, affective lexicon building, emotion scores, unsupervised settings, sentiment analysis

https://aclanthology.org/P14-2070/

https://www.semanticscholar.org/paper/Depeche-Mood%3A-a-Lexicon-for-Emotion-Analysis-from-Staiano-Guerini/492cefde909957fd8b0f77f75e51b066567671b6

https://aclanthology.org/P14-2070.pdf

https://app.razzi.my/findgref?gid=1_P_NOkeQQ0T5lUUS6qwW-qRUb9MFp1FI

Even though considerable attention has been given to the polarity of words (positive and negative) and the creation of large polarity lexicons, research in emotion analysis has had to rely on limited and small emotion lexicons.

In this paper, we show how the combined strength and wisdom of the crowds can be used to generate a large, high-quality, word–emotion and word–polarity association lexicon quickly and inexpensively.

We enumerate the challenges in emotion annotation in a crowdsourcing scenario and propose solutions to address them.

Most notably, in addition to questions about emotions associated with terms, we show how the inclusion of a word choice question can discourage malicious data entry, help to identify instances where the annotator may not be familiar with the target term (allowing us to reject such annotations), and help to obtain annotations at sense level (rather than at word level).

We conducted experiments on how to formulate the emotion-annotation questions, and show that asking if a term is associated with an emotion leads to markedly higher interannotator agreement than that obtained by asking if a term evokes an emotion.

Emotions, affect, polarity, semantic orientation, crowdsourcing, Mechanical Turk, emotion lexicon, polarity lexicon, word–emotion associations, sentiment analysis.

https://onlinelibrary.wiley.com/doi/10.1111/j.1467-8640.2012.00460.x

https://arxiv.org/pdf/1308.6297.pdf

https://www.semanticscholar.org/paper/CROWDSOURCING-A-WORD%E2%80%93EMOTION-ASSOCIATION-LEXICON-Mohammad-Turney/54227c063bb04489caffd65ff9fc6218788ddb25

https://www.researchgate.net/publication/256199465_Crowdsourcing_a_Word-Emotion_Association_Lexicon

https://app.razzi.my/findgref?gid=15LQdmmfNMwhK7jb-4zkPkKOjZ0apm6fz