Alert button
Picture for Fernanda B. Viégas

Fernanda B. Viégas

Alert button

Direct-Manipulation Visualization of Deep Networks

Aug 12, 2017
Daniel Smilkov, Shan Carter, D. Sculley, Fernanda B. Viégas, Martin Wattenberg

Figure 1 for Direct-Manipulation Visualization of Deep Networks
Figure 2 for Direct-Manipulation Visualization of Deep Networks
Figure 3 for Direct-Manipulation Visualization of Deep Networks
Figure 4 for Direct-Manipulation Visualization of Deep Networks

The recent successes of deep learning have led to a wave of interest from non-experts. Gaining an understanding of this technology, however, is difficult. While the theory is important, it is also helpful for novices to develop an intuitive feel for the effect of different hyperparameters and structural variations. We describe TensorFlow Playground, an interactive, open sourced visualization that allows users to experiment via direct manipulation rather than coding, enabling them to quickly build an intuition about neural nets.

Viaarxiv icon

Embedding Projector: Interactive Visualization and Interpretation of Embeddings

Nov 16, 2016
Daniel Smilkov, Nikhil Thorat, Charles Nicholson, Emily Reif, Fernanda B. Viégas, Martin Wattenberg

Figure 1 for Embedding Projector: Interactive Visualization and Interpretation of Embeddings
Figure 2 for Embedding Projector: Interactive Visualization and Interpretation of Embeddings

Embeddings are ubiquitous in machine learning, appearing in recommender systems, NLP, and many other applications. Researchers and developers often need to explore the properties of a specific embedding, and one way to analyze embeddings is to visualize them. We present the Embedding Projector, a tool for interactive visualization and interpretation of embeddings.

* Presented at NIPS 2016 Workshop on Interpretable Machine Learning in Complex Systems 
Viaarxiv icon