AI News, Picasso: A free open-source visualizer for Convolutional Neural Networks

Picasso: A free open-source visualizer for Convolutional Neural Networks

While it’s easier than ever to define and train deep neural networks (DNNs), understanding the learning process remains somewhat opaque.

Monitoring the loss or classification error during training won’t always prevent your model from learning the wrong thing or learning a proxy for your intended classification task.

To understand what we mean, consider this (possibly apocryphal) story [1]: Regardless of the veracity of this tale, the point is familiar to machine learning researchers: training metrics don’t always tell the whole story.

And the stakes are higher than ever before: for rising applications of deep learning like autonomous vehicles, these kinds of training errors can be deadly [2].

we developed Picasso to make it easy to see standard visualizations across our models in our various verticals: including applications in automotive, such as understanding when road segmentation or object detection fail;

We already know this model is pretty good at classifying tanks: can we use these visualizations to check that model is actually classifying based on the tank and not, say, the sky?

Picasso: A Modular Framework for Visualizing the Learning Process of Neural Network Image Classifiers

Neural networks (NNs) [1] and convolutional neural networks (CNNs) [2, 3, 4] are subject to unique training pitfalls [5, 6].

The researchers ran the neural network on the remaining 100 photos, and without further training the neural network classified all remaining photos correctly.

The researchers handed the finished work to the Pentagon, which soon handed it back, complaining that in their own tests the neural network did no better than chance at discriminating photos.

It turned out that in the researchers’ dataset, photos of camouflaged tanks had been taken on cloudy days, while photos of plain forest had been taken on sunny days.

[emphasis added] While this story may be apocryphal, it nonetheless illustrates a common pitfall in machine learning: training on a proxy feature instead of the intended feature.

We developed Picasso to help protect against situations where evaluation metrics like loss and accuracy may not tell the whole story in training neural networks on image classification tasks.

Picasso makes it easy to see standard visualizations across our models in various fields: including applications in automotive, such as understanding when road segmentation or object detection fail;

Other visualization packages exist to help bring transparency to the learning process, most notably the Deep Visualization Toolbox [15] and keras-vis [16], which can also generate saliency maps.

We furthermore required an application that would easily allow us to add new visualizations, which may in the future include visualizations such as class activation mapping [17, 18] and image segmentation [19, 20].

Lecture 12 | Visualizing and Understanding

In Lecture 12 we discuss methods for visualizing and understanding the internal mechanisms of convolutional networks. We also discuss the use of convolutional networks for generating new images,...

Rebecca Bilbro - Yellowbrick: Steering Machine Learning with Visual Transformers

Filmed at PyData London 2017 Description Yellowbrick is a new library that extends Scikit-Learn's API to incorporate visualizations into machine learning. While the machine learning workflow...

Lecture 1 | Introduction to Convolutional Neural Networks for Visual Recognition

Lecture 1 gives an introduction to the field of computer vision, discussing its history and key challenges. We emphasize that computer vision encompasses a wide variety of different tasks,...

Deep Dreaming Fear & Loathing in Las Vegas: the Great San Francisco Acid Wave

Deep neural network hallucinating Fear & Loathing in Las Vegas: how meta is that? Visualizing the internals of a deep net we let it develop further what it think it sees. code:

Extraordinary Variations of the Mind: Geschwind:Our Brains Berman: Williams SyndromeFisher:Language

Visit: 1:39 - Our Brains: Life on a Continuum 21:07 - From Genes to Neural Circuits 35:07 - Language at the Extremes The human mind is one of the features that makes..

Google I/O'17: Channel 7

Technical sessions and deep dives into Google's latest developer products and platforms. Watch more Firebase talks at I/O '17 here: See all the talks from Google I/O..

Hear about the state and future direction of the Azure Compute services

Microsoft Azure Compute services span from Infrastructure to application platform - VMs, Cloud Services, VM Scale Sets, Containers, Batch, Service Bus, Event Hub, Service Fabric and power the...

Introduction to Dictionary Skills

A charming introduction to first dictionary skills, to help every child understand how to use dictionaries to find the words they need, and enrich their language.

Collections as Data: Impact

Building on the success of its “Collections as Data” symposium last year, the Library of Congress National Digital Initiatives (NDI) again will host a daylong symposium featuring a cadre...


Young Adults discuss what self-advocacy means to them and how they advocate for themselves in school, work, and their daily lives. For more resources on self-advocacy and career exploration,...