TensorFlow Playground

TensorFlow Playground is an interactive web app that allows users to test artificial intelligence (AI) algorithms with Google’s TensorFlow machine learning libraries.

TensorFlow Playground allows users who are unfamiliar with high-level math and coding to experiment with neural networks for deep learning and other machine learning applications. Neural network operations are interactive and are represented visually in the Playground.

The TensorFlow Playground web app is built on Typescript using ds3.js. Through the browser, the user can run small neural networks, create experiments and get results. The included open source library is designed to meet educational requirements. Although small, the library is fast, flexible, scalable and ready to use for learning, research and production. Google also provides training and exercises to help users learn more about neural networks and machine learning.

TensorFlow gets its name from the data flow graphs from which numerical calculations are performed; the graphs represent mathematical operations through nodes and data through edges. The edges are generally multidimensional data arrays, or what is known as tensors. Google also uses the Tensor name for TPU (tensor processing unit), the company's AI accelerator ASIC.