Journal Article

Towards artificial general intelligence with hybrid Tianjic chip architecture

Deng, Ning, Li, Huanglong, Pei, Jing, Zou, Zhe, Wang, Yu, Ma, Cheng, Wu, Shuang, Zhao, Rong, Wang, Guanrui, Xie, Yuan, Han, Wentao, Wu, Zhenzhi, Song, Sen, Wu, Yujie, Wu, Huaqiang, Li, Guoqi, Deng, Lei, Wu, Si, Zhao, Mingguo, Yang, Zheyu, Chen, Feng, Zhang, Youhui, He, Wei, Shi, Luping

2019

Overview

There are two general approaches to developing artificial general intelligence (AGI) 1 : computer-science-oriented and neuroscience-oriented. Because of the fundamental differences in their formulations and coding schemes, these two approaches rely on distinct and incompatible platforms 2 – 8 , retarding the development of AGI. A general platform that could support the prevailing computer-science-based artificial neural networks as well as neuroscience-inspired models and algorithms is highly desirable. Here we present the Tianjic chip, which integrates the two approaches to provide a hybrid, synergistic platform. The Tianjic chip adopts a many-core architecture, reconfigurable building blocks and a streamlined dataflow with hybrid coding schemes, and can not only accommodate computer-science-based machine-learning algorithms, but also easily implement brain-inspired circuits and several coding schemes. Using just one chip, we demonstrate the simultaneous processing of versatile algorithms and models in an unmanned bicycle system, realizing real-time object detection, tracking, voice control, obstacle avoidance and balance control. Our study is expected to stimulate AGI development by paving the way to more generalized hardware platforms. The ‘Tianjic’ hybrid electronic chip combines neuroscience-oriented and computer-science-oriented approaches to artificial general intelligence, demonstrated by controlling an unmanned bicycle.

• Publisher: Nature Publishing Group UK,Nature Publishing Group
• Subject: 639/166/987 / 639/925/927/1007 / Algorithms / Artificial intelligence / Artificial neural networks / Bicycles / Brain / Coding / Computational neuroscience / Computer architecture / Design and construction / Equipment and supplies / Field programmable gate arrays / Formulations / Humanities and Social Sciences / Hybrid systems / Integrated circuits / Intelligence / Learning algorithms / Letter / Machine learning / Memory / multidisciplinary / Nervous system / Network topologies / Neural coding / Neural networks / Neurons / Neurosciences / Object recognition / Obstacle avoidance / Platforms / Science / Science (multidisciplinary) / Semiconductor chips / Technology application / Tracking control / Voice control / Voice recognition