Mar 28, 2018 · newsletter

New creative possibilities with machine learning

Machine learning techniques are able to organize large amounts of unstructured data. Combined with dimensionality reduction techniques like t-SNE, this capability opens up new ways for us to interact with creative material including sounds, words, and ideas. In this section we highlight three of our favorite recent experiments.

A screenshot of The Infinite Drum Machine. Showing the sample map with certain sounds like “Bag Plastic” highlighted and a drum sequencer at the bottom.

The Infinite Drum Machine is a Google Creative Lab experiment by Manny Tan and Kyle McDonald. It uses machine learning to cluster a large number of samples by similarity of sound. The user then selects clips, which can range from “gravel scoop tin cup” to “casino poker chip,” from a sound map visualization created using t-SNE. The samples feed into a sequencer to create an uncanny drum machine.

Conceptually, the project works because it plays off the long history of hip-hop and electronic musicians using samples from surprising sources (one of Grant’s favorite, kind of gross, examples is Matmos’ “A Chance to Cut is a Chance to Cure”). Sometimes machine learning systems give disappointing results because the system lacks context. In this case, the lack of context is a virtue. It frees the system up to make connections between sounds that humans, with their knowledge of each sound’s source, might never make. It reminds us of first learning to draw, where you have to let go of your idea of what an apple looks like and draw the apple exactly as it appears in front of you.

Samples map well because each sound has a quantifiable (wave) form. Anything involving words gets more complicated. Do you compare on similarity of phoneme, grapheme, or meaning?

A screenshot of an example from “Voyages in Sentence Space.” It shows this example:“I went looking for adventure. I went out on a mission. I shouted awkwardly. I stared incredulously. I feel desperate. I never returned. I never returned.

In Voyages in Sentence Space, Robin Sloan uses machine learning to explore the possibility space between sentences, which he calls “sentence gradients” (we love that metaphor). Instead of showing the whole map, it focuses on a specific journey from one sentence to another. As for how it does comparisons, Robin tweeted about one illustrative example where, according to the model, ‘“thousand” is more like “three” than it is like “hundred” because of the “th."’

A screenshot of Encartopedia. On the left is the Wikipedia article on Euclid. On the right is a visualization of the articles on Wikipedia and a line showing the user’s journey through other articles to get to the Euclid article.

Sepand Ansari’s Encartopedia, which he made while working with us here at CFFL, looks at visualizing Wikipedia articles as an idea map, and plotting the user’s journey through that space. It suggests how new capabilities can help us reflect on our thought process, by showing us how we move through an idea space.

Read more

Mar 28, 2018 · newsletter
Mar 6, 2018 · demo

Latest posts

Jun 22, 2020 · post

How to Explain HuggingFace BERT for Question Answering NLP Models with TF 2.0

by Victor · 199 // ... code -- Figure 1: In this sample, a BERTbase model gets the answer correct (Achaemenid Persia). Model gradients show that the token “subordinate ..” is impactful in the selection of an answer to the question “Macedonia was under the rule of which country?". This makes sense .. good for BERTbase. Recently, our team at Fast Forward Labs have been exploring state of the art models for Question Answering and have used the rather excellent HuggingFace transformers library. more
Jun 16, 2020 · notebook

Evaluating QA: Metrics, Predictions, and the Null Response →

by Melanie · A deep dive into computing QA predictions and when to tell BERT to zip it! In our last post, Building a QA System with BERT on Wikipedia, we used the HuggingFace framework to train BERT on the SQuAD2.0 dataset and built a simple QA system on top of the Wikipedia search engine. This time, we’ll look at how to assess the quality of a BERT-like model for Question Answering.
May 19, 2020 · notebook

Building a QA System with BERT on Wikipedia →

by Melanie · So you’ve decided to build a QA system. You want to start with something simple and general so you plan to make it open domain using Wikipedia as a corpus for answering questions. You want to use the best NLP that your compute resources allow (you’re lucky enough to have access to a GPU) so you’re going to focus on the big, flashy Transformer models that are all the rage these days.
Apr 28, 2020 · notebook

Intro to Automated Question Answering →

by Melanie · Welcome to the first edition of the Cloudera Fast Forward blog on Natural Language Processing for Question Answering! Throughout this series, we’ll build a Question Answering (QA) system with off-the-shelf algorithms and libraries and blog about our process and what we find along the way. We hope to wind up with a beginning-to-end documentary that provides:
Apr 1, 2020 · newsletter

Enterprise Grade ML

by Shioulin · At Cloudera Fast Forward, one of the mechanisms we use to tightly couple machine learning research with application is through application development projects for both internal and external clients. The problems we tackle in these projects are wide ranging and cut across various industries; the end goal is a production system that translates data into business impact. What is Enterprise Grade Machine Learning? Enterprise grade ML, a term mentioned in a paper put forth by Microsoft, refers to ML applications where there is a high level of scrutiny for data handling, model fairness, user privacy, and debuggability. more
Apr 1, 2020 · post

Bias in Knowledge Graphs - Part 1

by Keita · Introduction This is the first part of a series to review Bias in Knowledge Graphs (KG). We aim to describe methods of identifying bias, measuring its impact, and mitigating that impact. For this part, we’ll give a broad overview of this topic. image credit: Mediamodifier from Pixabay Motivation Knowledge graphs, graphs with built-in ontologies, create unique opportunities for data analytics, machine learning, and data mining. They do this by enhancing data with the power of connections and human knowledge. more

Popular posts

Oct 30, 2019 · newsletter
Exciting Applications of Graph Neural Networks
Nov 14, 2018 · post
Federated learning: distributed machine learning with data locality and privacy
Apr 10, 2018 · post
PyTorch for Recommenders 101
Oct 4, 2017 · post
First Look: Using Three.js for 2D Data Visualization
Aug 22, 2016 · whitepaper
Under the Hood of the Variational Autoencoder (in Prose and Code)
Feb 24, 2016 · post
"Hello world" in Keras (or, Scikit-learn versus Keras)


In-depth guides to specific machine learning capabilities


Machine learning prototypes and interactive notebooks


A usable library for question answering on large datasets.

Explain BERT for Question Answering Models

Tensorflow 2.0 notebook to explain and visualize a HuggingFace BERT for Question Answering model.

NLP for Question Answering

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

Interpretability Revisited: SHAP and LIME

Explore how to use LIME and SHAP for interpretability.


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