LAVIN  

2019  /  

An exploratory journey

inside a neural network in VR

VIDEO DOCUMENTATION ​[ 2 minutes ]

Screen Recording of A visitor's experience​

CREDIT 

Virtual Reality Worldbuilding

Art Direction & Creative Coding 

Weidi Zhang

Intelligent System Design

Creative Coding

Rodger Luo

EXHIBITIONS

SwissNex Gallery

San Francisco, 2019

ACM SIGGRAPH ART GALLERY

Los Angeles, 2019

M.A.D.E End of Year Show, CNSI

Santa Barbara, 2019

MEDIUM

5 - 10 minutes

Virtual Reality Art Installation

Enter Through the VR Headset

SPECIAL THANKS

Mengyu Chen 

Prof. Legrady and Experimental Vis Lab

LAVIN is a VR project is a conceptual response to Ground Truth in the modern AI age. From a neural network (NN) trained to recognize thousands of objects to a NN can only generate binary outputs, each NN, like human beings, has its own understanding of the real world, even the inputs are the same. LAVIN provides an immersive responsive experience to visually explore one understanding of a NN in which the real world is mapping to 50 daily objects. LAVIN constantly analyzes the real world via a camera and outputs semantic interpretations, which navigate the audience in a virtual world consisting of all the fluid abstract structures that designed and animated based on the photogrammetry of daily objects that the NN can recognize.

​​这个VR项目是对当今人工智能时代中 真实 的定义的艺术概念性的回答。 神经网络可以通过被训练 来认识成千上万的物体 输出二进制的回答,每个神经网络其实和人类一样,对真实的世界有着自己的理解。LAVIN 通过人工智能神经网络训练把真实的世界归类重组成五十个物件并通过VR技术视觉化的呈现在VR虚拟世界。LAVIN通过一个相机采集周围真实世界的数据,然后利用人工智能技术分析归类,得出一个物件的词语作为结论。每次人工智能分析完周围的数据,佩戴头盔的体验者就会被实时带到虚拟世界里相关物件的旁边。每次分析需要5 - 15秒时间,于是沉浸者通过人工智能持续性的错误理解这个世界来完成一趟虚拟世界的旅行。

The current AI technique allows a neural network to recognize over 20 thousand different categories of objects. Meanwhile, countless neural networks are trained for different applications that the outputs of each neural network is a unique projection of its own understanding of the real world. Regardless of the complexity of the projection, it shapes the “world value” of the neutral network it belongs. Therefore, an interesting question arises as to what ground truth is in the modern AI age, given the fact that the most complex neural network model cannot inclusively represent the real world. This VR project tries to address this question by providing an immersive responsive experience to evoke people’s awareness of regrading values and beliefs.

Photo Documentation ​

Screenshots of A visitor's experience​

目前的人工智能技术允许神经网络识别超过20000种不同类型的对象。同时,无数的神经网络被训练为不同的应用程序且每个神经网络的输出是它自己的理解现实世界的一个独特的投影。不管投影的复杂程度如何,它都塑造了它所属的神经网络的“世界价值”。因此,一个有趣的问题出现了,在现代人工智能时代,什么是真理,因为最复杂的神经网络模型不能包容地代表现实世界。这个虚拟现实项目试图通过提供身临其境的沉浸体验来让人们重新思考对价值和信仰的认知

PHOTO DOCUMENTATION ​

Screenshot of A visitor's experience​

Installation View / SIGGRAPH 2019, LOS ANGELES

All Rights Reserved. © 2020  Weidi Zhang