A new neural network modeling approach based on a correction model concept

Mendhurwar, Kaustubha; Raut, R.; Bhattacharya, Prabir; Khan, Zulfiqar Ali; Devabhaktuni, Vijay

doi:10.1109/apmc.2009.5384450

Cited by 4 publications

(8 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The simulation data is generated using a detailed HSPICE model, which then helps us to develop highly accurate neural models using the algorithms described in our previous papers [36][37][38][39]. A datasheet of simulation data is generated by sweeping the parameters within their minimum and maximum usable values.…”

Section: Ann Based Cadmentioning

confidence: 99%

“…These values strictly depend on the technology to be used. Correction models [38] are used for accurate evaluation of the design parameters. The modeling algorithms used for creating the neural models namely, binning algorithm and correction model algorithm are described below.…”

Section: Ann Based Cadmentioning

confidence: 99%

“…2. Neural models are developed using the algorithms proposed in our previous papers [36][37][38][39][40][41]. 3.…”

Section: Analog Ic Design Flowmentioning

confidence: 99%

See 2 more Smart Citations

A new approach to sizing analog CMOS building blocks using pre-compiled neural network models

Mendhurwar

Sundani

Aggarwal

et al. 2011

Analog Integr Circ Sig Process

Self Cite

View full text Add to dashboard Cite

There has been a constant endeavor towards improving the available circuit design automation tools to match technological advancements in the electronic industry. However, inadequate research efforts in the analog domain are holding back the exploitation of advanced technologies. A dearth of design expertise in the analog domain is the principal driving force for the growth of Design Automation (DA) tools. Transistor sizing is one of the most crucial steps in the analog IC design. In this paper, we put forward a new computer aided design framework for the sizing of transistors in MOS Integrated Circuit (IC) amplifiers by incorporating powerful modeling capabilities of Artificial Neural Networks (ANN). ANNs have proven to be efficient and accurate modeling tools in several applications. The proposed tool is capable of directly computing transistor related design parameters, of the MOS IC amplifier and associated peripheral circuitry. The proposed tool thus avoids several time-consuming simulations and/or tuning runs at the very bottom level of analog IC amplifier implementation, using a given CMOS process. It also reduces manual intervention in the design process, thus enhancing the automation of the design process. This paper presents design examples of several analog IC functional modules that are developed and verified successfully.

show abstract

Section: Ann Based Cadmentioning

confidence: 99%

Section: Ann Based Cadmentioning

confidence: 99%

See 1 more Smart Citation

A new approach to sizing analog CMOS building blocks using pre-compiled neural network models

Mendhurwar

Sundani

Aggarwal

et al. 2011

Analog Integr Circ Sig Process

Self Cite

View full text Add to dashboard Cite

show abstract

“…Alternatively, by applying the reverse modeling approach [35] to the coarse model, the translated intermediate inputs (latitude' and longitude') can be obtained corresponding to any given original latitude and longitude. Alternatively, by applying the reverse modeling approach [35] to the coarse model, the translated intermediate inputs (latitude' and longitude') can be obtained corresponding to any given original latitude and longitude.…”

Section: Kbnn Trainingmentioning

confidence: 99%

Knowledge‐based neural network approaches for modeling and estimating radon concentrations

Akkala

Bhatt

Devabhaktuni

et al. 2012

Env Prog and Sustain Energy

Self Cite

View full text Add to dashboard Cite

Radon is a chemically inert, tasteless, and odorless gas, which causes lung cancer in people who are exposed to higher concentrations for extended periods of time. It is a byproduct of the decay of uranium in the soil. High concentrations are present in closed units, like houses, schools, etc. To identify houses with unacceptably high radon levels, the radon concentration for each zip code in Ohio needs to be measured. However, not all of the zip codes are surveyed, owing to reasons such as inapproachability. In places where data is unavailable, the concentrations need to be estimated using interpolation techniques. This article proposes the application of knowledge‐based neural network approaches, namely prior knowledge input method, source difference method, and space‐mapped neural network method for modeling and predicting radon concentrations. To this end, knowledge available in the form of uranium concentration data is exploited. Modeling accuracies of the proposed techniques are compared with those of the commonly used multilayer perceptron networks (employed in one of our recent work) and conventional interpolation techniques. © 2012 American Institute of Chemical Engineers Environ Prog, 32: 355‐364, 2013

show abstract

“…To address this, a new technique referred to as correction model has been recently developed [12, 13]. The correction model, an intermediary model with high accuracy, is used to enhance the accuracy of the original model.…”

Section: Introductionmentioning

confidence: 99%

Sensitivity driven artificial neural network correction models for RF/microwave devices

Devabhaktuni

Mareddy

Vemuru

et al. 2011

Int J RF and Microwave Comp Aid Eng

Self Cite

View full text Add to dashboard Cite

In this article, we propose a sensitivity based correction model that improves the accuracy of the neural model keeping the structure of artificial neural network (ANN) simple. The proposed approach is applied to the modeling of RF transistors, spiral inductors, and microstrip antennas. Results are compared with conventional ANN and a recent technique referred to as correction model that is assisted by the regula-falsi method.

show abstract

A new neural network modeling approach based on a correction model concept

Cited by 4 publications

References 5 publications

A new approach to sizing analog CMOS building blocks using pre-compiled neural network models

A new approach to sizing analog CMOS building blocks using pre-compiled neural network models

Knowledge‐based neural network approaches for modeling and estimating radon concentrations

Sensitivity driven artificial neural network correction models for RF/microwave devices

Contact Info

Product

Resources

About