AI Experiments

Machine learning prototypes, demos, and code by Cloudera Fast Forward.
Blog

NLP for Question Answering

Ongoing posts and code documenting the process of building a question answering model.
Notebook

Interpretability Revisited: SHAP and LIME

Explore how to use LIME and SHAP for interpretability.
Report

Interpretability

Learn about using interpretability techniques on deep learning models.
Prototype

Refractor

Refractor predicts churn probabilities for telecom customers and shows which customer attributes contribute to those predictions.
Prototype

Anomagram

An interactive visualization tool for exploring how a deep learning model can be applied to the task of anomaly detection.
Report

Deep Learning for Anomaly Detection

Learn how to use deep learning approaches (including sequence models, VAEs, and GANS) for anomaly detection.
Prototype

Blip

Blip visualizes how four different anomaly detection algorithms perform at detecting network attacks.
Demo

Squote

A semantic search engine that takes some input text and returns relevant famous quotes.
Report

Textflix Report

Learn about how we used transfer learning and a pretrained BERT model to build our sentiment analysis prototype.
Prototype

Textflix

Textflix uses movie reviews to show how machine learning can unlock the data embedded in large amounts of unstructured text.
Prototype

ConvNet Playground

With ConvNet Playground you can explore how a convolutional neural network does semantic image search.
Notebook

Weak supervision with Snorkel

A notebook showing how to train a complaint classifier with Snorkel. Using data from the Consumer Financial Protection Bureau.
Prototype

Active Learner

An interactive visualization of active learning data labeling strategies for supervised machine learning.
Library

Handtrack.js

Handtrack.js is a library for prototyping realtime hand detection (bounding box), directly in the browser.
Demo

UMAP Explorer

An interactive UMAP visualization of the MNIST data set.
Demo

Active Learning with Logistic Regression

A toy example about logistic regression and different active learning strategies.
Prototype

Turbofan Tycoon

See if you have what it takes to make it as a turbofan factory owner in our federated learning prototype.
Prototype

Probabilistic Real Estate

A probabilistic programming prototype that predicts future real estate prices across New York City boroughs and neighborhoods.
Prototype

Brief Preview

Brief uses neural networks to score and highlight the most interesting sentences within any article.
Tutorial

Using three.js for 2D Data Visualization

An interactive notebook about using three.js to render tens of thousands of points.
Demo

Encartopedia

Encartopedia visualizes Wikipedia topic clusters and plots your journey through them.
Demo

Visualizing the Taste of a Community of Cinephiles

An interactive visualization that uses T-SNE to cluster movies together based on user ratings.
Demo

Luhn Method Demo

Luhn's method, from 1958, provides a foundation for understanding modern auto-summarization techniques.

About

Cloudera Fast Forward is an applied machine learning research group.
Cloudera  Blog  Twitter