Skip to content

FelixKleineBoesing/FruitFlyEmbeddings

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

15 Commits
 
 
 
 
 
 
 
 

Repository files navigation

FruitFlyEmbeddings

tensorflow implementation of the FruitFlyEmbeddings Paper

Background

Some Researches proposed a model that is strongly based on the neural net of a fruit fly. They asked whether it is possible to create meaningful embeddings with this simple network.

model architecture

Goal

I want to implement the proposed architecture. Instead of word embeddings I will use market baskets to build product embeddings for an online retailer. This decision is solely based on the fact, that I do not want so spend ~1 day with training and therefore came up with an use cases that is a lot easier to interpret whiel having the same nature of embeddings.

Setup

Download the dataset from kaggle and put it into a directory called "data".

Install all requirements:

pip3 install -r requirements.txt

About

My own implementation of the FruitFlyEmbeddings Paper

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages