Actions

Difference between revisions of "Algoliterary Encounters"

From Algolit

(How the Machine Reads: Dissecting Neural Networks)
Line 35: Line 35:
 
* [[A Bag of Words]]
 
* [[A Bag of Words]]
 
* [[A One Hot Vector]]
 
* [[A One Hot Vector]]
 +
 +
==== Special Focus: Word Embeddings ====
 
* [[word embeddings]]
 
* [[word embeddings]]
 +
* [[Crowd Embeddings]] - case studies, still needs fine tuning
  
==== Different views on the data ====
+
===== Different portraits of word embeddings =====
 
* [[Word embedding Projector]]
 
* [[Word embedding Projector]]
 
* [[5 dimensions 32 graphs]]
 
* [[5 dimensions 32 graphs]]
 
* [[The GloVe Reader]]
 
* [[The GloVe Reader]]
  
==== Creating word embeddings using word2vec ====
+
===== Inspecting the technique =====
* [[Crowd Embeddings]] - case studies, still needs fine tuning
 
 
* [[word2vec_basic.py]] - in piles of paper
 
* [[word2vec_basic.py]] - in piles of paper
 
* [[softmax annotated]]
 
* [[softmax annotated]]

Revision as of 16:05, 25 October 2017


Start of the Algoliterary Encounters catalog.

Introduction

Algoliterary works

Algoliterary explorations

What the Machine Writes: a closer look at the output

How the Machine Reads: Dissecting Neural Networks

Datasets

From words to numbers

Special Focus: Word Embeddings

Different portraits of word embeddings
Inspecting the technique

How a Machine Might Speak

Sources

Bibliography