From Tinkering to Engineering: Measurements in Tensorflow Playground
This tool aims to improve experimental design and reproducibility for neural network practitioners by educating them on available information-theoretic measurements.
This paper introduces Tensorflow Meter (TFMeter), an extension of Tensorflow Playground that visually displays information-theoretic measurements during neural network construction, training, and testing. The tool aims to provide users with a better engineering intuition about how different architectures learn by showing how each change impacts various measurements.
In this article, we present an extension of the Tensorflow Playground, called Tensorflow Meter (short TFMeter). TFMeter is an interactive neural network architecting tool that allows the visual creation of different architectures of neural networks. In addition to its ancestor, the playground, our tool shows information-theoretic measurements while constructing, training, and testing the network. As a result, each change results in a change in at least one of the measurements, providing for a better engineering intuition of what different architectures are able to learn. The measurements are derived from various places in the literature. In this demo, we describe our web application that is available online at http://tfmeter.icsi.berkeley.edu/ and argue that in the same way that the original Playground is meant to build an intuition about neural networks, our extension educates users on available measurements, which we hope will ultimately improve experimental design and reproducibility in the field.