3D neural network visualization with TensorSpace /

"TensorSpace is a neural network 3D visualization framework built by TensorFlow.js, Three.js, and Tween.js. TensorSpace provides Keras-like APIs to build deep learning layers, load pre-trained models, and generate a 3D visualization in the browser. By applying TensorSpace API, it is more intuit...

Full description

Bibliographic Details
Other Authors:	Konczyk, Jakub (Speaker)
Format:	Video
Language:	English
Published:	[Place of publication not identified] : Packt, [2019]
Subjects:	Information visualization. Neural networks (Computer science) JavaScript (Computer program language) Machine learning. Neural Networks, Computer Visualisation de l'information. Réseaux neuronaux (Informatique) JavaScript (Langage de programmation) Apprentissage automatique. Instructional films. Films de formation.
Online Access:	Connect to this streaming video (Alexander Street Press)

Description
Summary:	"TensorSpace is a neural network 3D visualization framework built by TensorFlow.js, Three.js, and Tween.js. TensorSpace provides Keras-like APIs to build deep learning layers, load pre-trained models, and generate a 3D visualization in the browser. By applying TensorSpace API, it is more intuitive for Data Scientists to visualize and understand any pre-trained models built by TensorFlow, Keras, TensorFlow.js, and so on. In this quick and short course, you'll learn how to present the inner workings of your pre-trained Neural Network models with easy-to-access 3D visualizations in a web browser. By the end of this course, you'll be able to create compelling 3D visualizations that will show the neural network architecture and how pre-trained models work in real time with TensorSpace."--Resource description page
Item Description:	Title from title screen (viewed April 26, 2019). Date of publication from resource description page.
Physical Description:	1 online resource (1 streaming video file (55 min., 33 sec.))