The Why, What, and How of Artificial General Intelligence Chip Development

被引:15
作者
James, Alex P. [1 ,2 ]
机构
[1] Kerala Univ Digital Sci Innovat & Technol, Sch Elect Syst & Automat, Trivandrum 695316, Kerala, India
[2] Indian Inst Informat Technol & Management Kerala, Ctr Artificial Gen Intelligence & Neuromorph Syst, Technopk, Kazhakkotam 695581, India
关键词
Artificial intelligence; Task analysis; Hardware; AI accelerators; Buildings; Testing; Chip scale packaging; AI chips; AI hardware; artificial general intelligence (AGI); edge AI; NEURAL-NETWORK; ACCELERATOR; INTEGRATION; DROPOUT; TIME;
D O I
10.1109/TCDS.2021.3069871
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The AI chips increasingly focus on implementing neural computing at low power and cost. The intelligent sensing, automation, and edge computing applications have been the market drivers for AI chips. Increasingly, the generalisation, performance, robustness, and scalability of the AI chip solutions are compared with human-like intelligence abilities. Such a requirement to transit from application-specific to general intelligence AI chip must consider several factors. This article provides an overview of this cross-disciplinary field of study, elaborating on the generalisation of intelligence as understood in building artificial general intelligence (AGI) systems. This work presents a listing of emerging AI chip technologies, classification of edge AI implementations, and the funnel design flow for AGI chip development. Finally, the design consideration required for building an AGI chip is listed along with the methods for testing and validating it.
引用
收藏
页码:333 / 347
页数:15
相关论文
共 116 条
[1]   An Accelerated LIF Neuronal Network Array for a Large-Scale Mixed-Signal Neuromorphic Architecture [J].
Aamir, Syed Ahmed ;
Stradmann, Yannik ;
Mueller, Paul ;
Pehle, Christian ;
Hartel, Andreas ;
Gruebl, Andreas ;
Schemmel, Johannes ;
Meier, Karlheinz .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS, 2018, 65 (12) :4299-4312
[2]   Efficiency and cost of economical brain functional networks [J].
Achard, Sophie ;
Bullmore, Edward T. .
PLOS COMPUTATIONAL BIOLOGY, 2007, 3 (02) :174-183
[3]   The hard problem of AI rights [J].
Andreotta, Adam J. .
AI & SOCIETY, 2021, 36 (01) :19-32
[4]  
[Anonymous], 2007, COLLECTION DEFINITIO
[5]  
[Anonymous], 2019, PUT TEST ENTHUSIASM, DOI 10.1287%2Flytx.2019.03.23n
[6]  
[Anonymous], ARTIFICIAL GEN INTEL, DOI DOI 10.1007/978-3-540-68677-4_10
[7]  
[Anonymous], 2015, Proceedings of the 25th Edition on Great Lakes Symposium on VLSI, DOI [DOI 10.1145/2742060.2743766, 10.1145/2742060.2743766]
[8]  
[Anonymous], 2013, Artificial Intelligence, Evolutionary Computing and Metaheuristics: In the Footsteps of Alan Turing, DOI DOI 10.1007/978-3-642-29694-9_1
[9]  
[Anonymous], 1987, Intelligence: Its structure, growth and action
[10]   Z*-Numbers, Data Structures, and Thinking in Machine-Mind Architecture [J].
Banerjee, Romi ;
Pal, Sankar K. .
IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE, 2020, 4 (05) :686-695