This repository has been archived by the owner. It is now read-only.
Joint Vector Spaces
Switch branches/tags
Nothing to show
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
analysis/ssd
attalos
sandbox
.gitignore
Dockerfile.caffe
Dockerfile.domino
Dockerfile.keras
Dockerfile.notebook
Dockerfile.nvidia
Dockerfile.tf
Dockerfile.theano
Dockerfile.torch
LICENSE
Makefile
README.md
bootstrap.sh
build.sh
requirements.txt
run.sh
setup.py

README.md

Attalos

This project explores methods in constructing a common representation across modalities using unstructured and heterogeneous data collections. This representation will be a joint vector space that can be used to compare concepts in a numerical manner, no matter how different the modality or type of concepts are. The type of data can vary widely and will range from images to text to social structure, but comparisons between them will be seamless and can be made with Euclidean operations. In other words, concepts that are proximal in the joint vector space will be exhibit semantic similarity. Lab41 will evaluate the vector space using well-known metrics on classification tasks.

Getting Started

To start downloading datasets, see the Dataset README.

To learn how to preprocess data, see the Preprocessing READE.

To learn about running the performance metrics, see the Evaluation README.

To learn how to optimize wordvectors, see the Update-words README.

To learn how to run the demo app, see the Demo README.

To learn about our utilities classes, see the Util README.

Install Instructions

git clone https://github.com/Lab41/attalos.git
cd attalos
make

Required Dependencies

  • Docker
  • make

Contributing to Attalos

Want to contribute? Awesome! Issue a pull request or see more details here.