Nonlinear vector autoregression excels at reservoir computing benchmark tasks and requires even shorter training data sets and training time, heralding the next generation of reservoir computing.
Abstract:
“Reservoir computing is a best-in-class machine learning algorithm for processing information generated by dynamical systems using observed time-series data. Importantly, it requires very small training data sets, uses linear optimization, and thus requires minimal computing resources. However, the algorithm uses randomly sampled matrices to define the underlying recurrent neural network and has a multitude of metaparameters that must be optimized. Recent results demonstrate the equivalence of reservoir computing to nonlinear vector autoregression, which requires no random matrices, fewer metaparameters, and provides interpretable results. Here, we demonstrate that nonlinear vector autoregression excels at reservoir computing benchmark tasks and requires even shorter training data sets and training time, heralding the next generation of reservoir computing.”
View this open access technical paper here. Published 09/2021. Find Ohio State University’s news article here.
Gauthier, D.J., Bollt, E., Griffith, A. et al. Next generation reservoir computing. Nat Commun 12, 5564 (2021).
Increasing complexity, disaggregation, and continued feature shrinks add to problem; oversight is scant.
Academia, industry partnerships ramp to entice undergrads into hardware engineering.
Packaging and inspection companies draw funding; 124 startups raise over $2.3 billion.
Pitches continue to decrease, but new tooling and technologies are required.
Buried features and re-entrant geometries drive application-specific metrology solutions.
While terms often are used interchangeably, they are very different technologies with different challenges.
Technology and business issues mean it won’t replace EUV, but photonics, biotech and other markets provide plenty of room for growth.
Commercial chiplet marketplaces are still on the distant horizon, but companies are getting an early start with more limited partnerships.
Existing tools can be used for RISC-V, but they may not be the most effective or efficient. What else is needed?
How customization, complexity, and geopolitical tensions are upending the global status quo.
The industry is gaining ground in understanding how aging affects reliability, but more variables make it harder to fix.
Key pivot and innovation points in semiconductor manufacturing.
Tools become more specific for Si/SiGe stacks, 3D NAND, and bonded wafer pairs.
Leave a Reply