Actions

Algoliterary Encounters: Difference between revisions

From Algolit

Line 29: Line 29:
  
 
==== Elements of Neural Networks ====
 
==== Elements of Neural Networks ====
 +
 +
===== input (datasets) =====
 +
 +
* posters with literary works that are readable for machines and escape copyright
 +
 +
* public domain dataset
 +
 +
===== text-to-numbers / vectors =====
 +
 +
* posters of matrices
 +
 +
* bag-of-words: physical book vector exercise (with multiple books or with one book)
 +
 +
* poster word embeddings one-hot-vector script
 +
 +
* annotated word2vec script http://www.algolit.net/scripts/word2vec_annotated/ - Manetta
 +
 +
    ===== layers, nodes, weights =====
 +
 +
* backpropagation (linear algebra, influence of weight on network)
 +
 +
    ===== multidimensionality =====
 +
 +
* digital interactive visualisation & printed visualisation 1 poster for 1 dimension (total could be 30 posters)
 +
 +
 
 +
    ===== algorithms/nodes =====
 +
 +
* softmax poster/booklet with comments on code & output
 +
 +
* visualisations
 +
 +
* playground.tensorflow.org javascript
 +
 +
   
 +
===== output =====
  
 
==== Datasets ====
 
==== Datasets ====

Revision as of 12:49, 3 October 2017

Start of the Algoliterary Encounters catalog.

General Introduction

Overview of Techniques

Rule-based agents
Classic Machine Learning
Neural Networks


Elements of Neural Networks

input (datasets)
  • posters with literary works that are readable for machines and escape copyright
  • public domain dataset
text-to-numbers / vectors
  • posters of matrices
  • bag-of-words: physical book vector exercise (with multiple books or with one book)
  • poster word embeddings one-hot-vector script
   ===== layers, nodes, weights =====
  • backpropagation (linear algebra, influence of weight on network)
   ===== multidimensionality =====
  • digital interactive visualisation & printed visualisation 1 poster for 1 dimension (total could be 30 posters)


   ===== algorithms/nodes =====
  • softmax poster/booklet with comments on code & output
  • visualisations
  • playground.tensorflow.org javascript


output

Datasets

  • Context of Neural Networks
  • Frameworks & Existing Communities
  • Algoliterary Works by Others