Articles
September 19, 2021

Here is the future of conversational AI

Unearth the future of conversational AI and how Raffle places itself in AI history.
Read More
September 2, 2021

Open source makes it easier to use deep learning

Read more on how open source increases the ease of using deep learning and how Raffle has built on this technology.
Read More
March 8, 2021

The future of conversational AI

Find out what the future of conversational AI has to offer and how Raffle plans to be a part of technological innovation.
Read More
January 8, 2021

How language modelling has changed NLP

This is the first of a series of four posts about the technology behind Raffle products, the future of AI, and NLP.
Read More
January 8, 2021

How we use open source deep learning models

Discover Raffle's deep learning framework and models to create our unique AI algorithms that are the core of our products.
Read More
December 18, 2018

End-to-end information extraction from documents

The Attend, Copy, Parse architecture is a deep neural network model trained on end-to-end data, that bypasses the need for word-level labels
Read More
November 21, 2017

Recurrent Relational Networks for Complex Relational Reasoning

Learn more about recurrent relational networks to train AI to mimic human behaviors.
Read More
April 3, 2017

Semi-supervised generation with cluster-aware generative models

Deep generative models trained with large amounts of unlabelled data have proven to be powerful within the domain of unsupervised learning.
Read More
January 1, 2017

Hash embeddings for efficient word representations

Learn more about hash embeddings, an efficient method for representing words in a continuous vector form.
Read More
January 1, 2017

A disentangled recognition and nonlinear dynamics model for Unsupervised Learning

Dive into the conversation around unsupervised learning and its impact within Raffle to understand our unique structure.
Read More
October 20, 2016

Neural machine translation with characters and hierarchical encoding

We propose a Neural Machine Translation model with a hierarchical char2word encoder that takes individual characters as input and output.
Read More
February 17, 2016

Auxiliary deep generative models

Deep generative models have recently achieved state-of-the-art performance in unsupervised and semi-supervised learning.
Read More
December 31, 2015

Autoencoding beyond pixels using a learned similarity metric

We present an autoencoder that leverages learned representations to better measure similarities in data space.
Read More
Don't miss any update!