Actions

Algoliterary Encounters: Difference between revisions

From Algolit

m
Line 21: Line 21:
 
=== How the Machine Reads: Dissecting Neural Networks ===
 
=== How the Machine Reads: Dissecting Neural Networks ===
 
==== Datasets ====
 
==== Datasets ====
 +
Working with Neural Networks includes collecting big amounts of textual data.
 +
A comparison with the collection of words of the Library of St-Gilles:
 
* [[Many many words]]  
 
* [[Many many words]]  
* [[The data (e)speaks]]
 
  
 
=====Common public datasets=====
 
=====Common public datasets=====
 +
Most commonly used public datasets are gathered at [https://aws.amazon.com/public-datasets/ Amazon].
 +
We looked closely at the following two:
 
* [[Common Crawl]]  
 
* [[Common Crawl]]  
 
* [[WikiHarass]]
 
* [[WikiHarass]]
  
 
=====Algoliterary datasets=====
 
=====Algoliterary datasets=====
* [[Frankenstein]]
+
Working with literary texts allows for poetic beauty in the reading/writing of the algorithms.
* [[Learning from Deep Learning]]
+
This is a small collection used for experiments.
* [[nearbySaussure]]
+
* [[The data (e)speaks]]
* [[astroBlackness]]
 
  
 
==== From words to numbers ====
 
==== From words to numbers ====

Revision as of 08:32, 2 November 2017

Algoliterary Encounters

Algoliterary works

A selection of works made by the members of Algolit over the past years.

Algoliterary explorations

This chapter presents part of the research of Algolit over the past two years.

What the Machine Writes: a closer look at the output

Two neural networks are presented more closely, what content do they produce?

How the Machine Reads: Dissecting Neural Networks

Datasets

Working with Neural Networks includes collecting big amounts of textual data. A comparison with the collection of words of the Library of St-Gilles:

Common public datasets

Most commonly used public datasets are gathered at Amazon. We looked closely at the following two:

Algoliterary datasets

Working with literary texts allows for poetic beauty in the reading/writing of the algorithms. This is a small collection used for experiments.

From words to numbers

As machine learning is based on statistics and math, in order to process text, words need to be transformed to numbers. In the following section we present three technologies to do so.

Different vizualisations of word embeddings
Inspecting the technique behind word embeddings

How a Machine Might Speak

If a neural net work could speak, what would it say?

Sources