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

Abstract : 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 paper 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.
 EXISTING SYSTEM :
 ? Therefore, users have an incentive to replace existing 7 nm node chips (assuming they do not break down) only when expecting to use 5 nm node chips for 8.8 years. Figure 9 shows node-to-node comparisons between 90 nm and 5 nm. We find that the timeframe where these costs become equal has increased, with a dramatic rise at the 7 versus 5 nm comparison. ? Training involves additional computations. First, the classification of training data from a forward pass is compared with an existing correct label to determine the degree of classification error. Second, a “gradient descent” computation backward propagates the error through the DNN to update the DNN’s parameters to better match and learn from the training data
 DISADVANTAGE :
 ? Most, if not all, AI chips on the market today including those aim towards early AGI natives are good at solving one or other weak-AI problems, at much lower energy and on-chip area compared to serverbased alternatives.Since the processing is done within the edge devices, the response times improve and it becomes closer to being suitable for real-time use. ? The agent can be implemented in the form of a software or hardware or more likely a combination of both in AI hardware perspective. Such agents if they were to survive diverse challenges would need the ability to reason, plan, solve problems, think abstractly, comprehend complex ideas, learn quickly and learn from experience.
 PROPOSED SYSTEM :
 • In fact, at top AI labs, a large portion of total spending is on AI-related computing. With general-purpose chips like CPUs or even older AI chips, this training would take substantially longer to complete and cost orders of magnitude more, making staying at the research and deployment frontier virtually impossible. • All computer chips—including general-purpose CPUs and specialized ones like AI chips—benefit from smaller transistors, which run faster and consume less energy than larger transistors. Compared to CPUs, AI chips also gain efficiency and speed for AI applications through AI-optimized designs.
 ADVANTAGE :
 ? The brain is considered as the benchmark system for AGI research. There are many approaches in neuromorphic computation that aim for achieving energy efficiency and performance benchmarks of the brain . ? The performance of the AI systems has considerably improved due to the availability of high-performance computers and excessive capturing of labeled data. ? The hardware performance of digital neural chips is assessed based on MAC operations per second (i.e. two floating point operations), throughput and clock frequency. ? Only about 10% of area in the chip is occupied by neurons, while the rest is occupied by memory units and control circuits.

We have more than 145000 Documents , PPT and Research Papers

Have a question ?

Mail us : info@nibode.com