Google has developed open source library called Deeplearn.js to enable an integrated machine learning experience on Chrome browser. The library helps to train neural networks without requiring any app installations.
Deeplearn.js is designed to perform interactive explanations for rapid prototyping and visualisation using Chrome. The library can also be used for offline computations. It exploits WebGL to perform computations on a GPU level.
“There are many reasons to bring machine learning (ML) into the browser. A client-side ML library can be a platform for interactive explanations, rapid prototyping and visualisation, and even for offline computation,” Google’s Big Picture team, comprising software engineers Nikhil Thorat and Daniel Smilkov, writes in a blog post.
Based on Python
Google claims that the library gets past the speed limits of JavaScript. The structure of Deeplearn.js is similar to the TensorFlow library and NumPy. Both these Python-based scientific computing packages are widely used in various machine learning applications.
Deeplearn.js comes with options for exporting weights from TensorFlow checkpoints. Authors can even import TensorFlow components in Deeplearn.js interface. Additionally, developers have the option to use the library with JavaScript.
You can find the initial list of Deeplearn.js demo projects on its official website. Furthermore, the Deeplearn.js code is available for access in a GitHub repository.
