How Robust Is a Probabilistic Neural VLSI System Against Environmental Noise

Lu, Chih‐Cheng; Li, C. C.; Chen, H.

doi:10.1007/978-3-540-69939-2_5

Cited by 3 publications

(2 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The CRBM [4][5][6] uses unsupervised training modulation parameters to study the characteristics of data distribution. This learning algorithm is based on minimizing contrastive divergence (referred to as MCD) to modulate parameters Wij to enable the output sampling distribution of visible operands to have the same distribution as the data.…”

Section: Digital Crbm Algorithm Circuit System Designmentioning

confidence: 99%

Towards a fully integrated electronic nose SoC

Chiu

Wang

Lin

et al. 2012

2012 IEEE 55th International Midwest Symposium on Circuits and Systems (MWSCAS)

View full text Add to dashboard Cite

Electronic noses (e-nose) have been studied for several years and extensively applied; however, they are limited by their volume and high manufacturing cost. Portable devices have become popular in recent years; therefore, it is crucial to integrate e-noses in portable devices (e.g., mobile phones). This study used TSMC 90nm 1P9M CMOS MSG technology to develop a front-end system-on-chip (SoC) for an electronic nose. The SoC contained interdigitated electrodes, multi-channel sensor interface circuits, an analog to digital converter, and a digital continuous restricted Boltzmann machine (CRBM). Various conducting-polymer materials were titrated on the interdigitated electrodes to form an on-chip sensor array. This SoC was controlled through an external microcontroller to perform odor identification and analysis. The simulation results of the SoC and gas classification show that this chip is suitable for portable applications and further integration.

show abstract

Section: Digital Crbm Algorithm Circuit System Designmentioning

confidence: 99%

Towards a fully integrated electronic nose SoC

Chiu

Wang

Lin

et al. 2012

2012 IEEE 55th International Midwest Symposium on Circuits and Systems (MWSCAS)

View full text Add to dashboard Cite

show abstract

“…Although analogue circuits are more vulnerable to noise interferences and hardware non-idealities, stochastic behaviour in analogue circuits can actually dis courage the propagation of computational errors and thus enhance the robustness against interferences and errors, as [7]. The proposed DN system in VLSI is thus designed to exhibit noise-induced, continuous-valued stochastic behaviour as [8].…”

Section: Introductionmentioning

confidence: 99%

Mapping the Diffusion Network into a stochastic system in Very Large Scale Integration

Chien

Chen

2010

The 2010 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

The Diffusion Network (DN) is a probabilistic model capable of recognising continuous-time, continuous valued biomedical data. As the stochastic process of the DN is described by stochastic differential equations, realising the DN with analogue circuits is important to facilitate real-time simulation of a large network. This paper presents the trans lation of the DN into analogue Very Large Scale Integration (VLSI). With extensive simulation, the dynamic ranges of parameters and their representation in VLSI are identified.The VLSI circuits realising the stochastic unit of the DN are further designed and interconnected to form a stochastic system using noise to induce stochastic dynamics in VLSI. The circuit simulation demonstrate that the VLSI translation of the DN is satisfactory and the DN system is capable of using noise-induced stochastic dynamics to regenerate various types of continuous time sequences. I. I NTRODUCTIONThe Diffusion Network (DN) proposed by Movellan is a stochastic recurrent network whose stochastic dynamics can be trained to model the probability distributions of continuous-time sequences by the Monte-Carlo Expectation Maximisation (EM) algorithm [1], [2]. As stochasticity is useful for generalising the natural variability in data [3][4], the DN is further shown suitable for recognising noisy, continuous-time biomedical data [5]. However, the stochastic dynamics of the DN is defined by a set of continuous-time, stochastic differential equations. The speed of simulating stochastic differential equations in a digital computer is inherently limited by the serial processing and numerical iterations of the computer. Translating the DN into analogue circuits is thus important for simulating a large DN in real time. The hardware implementation of the DN could further function as an intelligent embedded system capa ble of recognising in real time multichannel, time-varying biomedical signals, for example, the neural activity recorded by a microprobe array in a brain-machine interface. In such applications, a DN system would enable implantable mi crosystems to deliver bio-feedbacks or to control prosthetic devices in real time [6].This paper presents the translation of the DN into a stochastic VLSI system using analogue circuits with noise induced stochasticity. Although analogue circuits are more vulnerable to noise interferences and hardware non-idealities, stochastic behaviour in analogue circuits can actually dis courage the propagation of computational errors and thus enhance the robustness against interferences and errors, as 978-1-�8lWtle1$26':PO ©201 0 IEEE demonstrated in [7]. The proposed DN system in VLSI is thus designed to exhibit noise-induced, continuous-valued stochastic behaviour as [8]. Following a brief review on the DN model, the dynamic ranges of parameters essential for modelling data satisfactorily are first identified with Matlab simulation. The representation of parameters in VLSI are then defined, and the component circuits for realising the DN are designed. Finally, the si...

show abstract

An Adaptable Continuous Restricted Boltzmann Machine in VLSI for Fusing the Sensory Data of an Electronic Nose

Wang

Tang

Chen

2017

IEEE Trans. Neural Netw. Learning Syst.

View full text Add to dashboard Cite

An embedded system capable of fusing sensory data is demanded for many portable or implantable microsystems. The continuous restricted Boltzmann machine (CRBM) is a probabilistic neural network not only capable of classifying data reliably but also amenable to very-large-scale-integration (VLSI) implementation. Although the embedded system based on the CRBM has been demonstrated with analog VLSI, the precision required by the learning algorithm is hardly achievable with analog circuits. Therefore, this paper investigates the feasibility of realizing the CRBM as a digital embedded system for fusing the sensory data of an electronic nose (eNose). The fusion here refers to data clustering and dimensional reduction that facilitates reliable classification. The capability of the CRBM to model different types of eNose data is first examined by MATLAB simulation. Afterward, the CRBM algorithm is customdesigned as a digital embedded system within an eNose microsystem. The functionality of the embedded CRBM system is then tested and discussed. With on-chip learning ability, the CRBM-embedded eNose is able to adapt its parameters in response to new data inputs or environmental changes.

show abstract

How Robust Is a Probabilistic Neural VLSI System Against Environmental Noise

Cited by 3 publications

References 7 publications

Towards a fully integrated electronic nose SoC

Towards a fully integrated electronic nose SoC

Mapping the Diffusion Network into a stochastic system in Very Large Scale Integration

An Adaptable Continuous Restricted Boltzmann Machine in VLSI for Fusing the Sensory Data of an Electronic Nose

Contact Info

Product

Resources

About