An FPGA multiprocessor architecture for Bayesian online change point detection using stochastic computation

Figliolia, Tomas; Andreou, Andreas G.

doi:10.1016/j.micpro.2019.102968

Cited by 4 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, they don't consider semi-structured sequential data and generate change probabilities using a single element of sequences. Thus, it is impossible to apply their approach to sequential data with complex dynamics.A natural improvement is to use recurrent neural network architectures [7,10] for change point and anomaly detection [15,6]. It provides high-quality models in supervised problems and can be used for various data types.…”

Section: Classic Methodsmentioning

confidence: 99%

InDiD: Instant Disorder Detection via Representation Learning

Romanenkova¹,

Stepikin²,

Morozov³

et al. 2021

Preprint

View full text Add to dashboard Cite

Change points are abrupt alterations in the distribution of sequential data. A change-point detection (CPD) model aims at quick detection of such changes. Classic approaches perform poorly for semi-structured sequential data because of the absence of adequate data representation learning. To deal with it, we introduce a principled differentiable loss function that considers the specificity of the CPD task. The theoretical results suggest that this function approximates well classic rigorous solutions. For such loss function, we propose an end-to-end method for the training of deep representation learning CPD models. Our experiments provide evidence that the proposed approach improves baseline results of change point detection for various data types, including real-world videos and image sequences, and improve representations for them. * This work is supported by the Russian Science Foundation (project 20-71-10135) Preprint. Under review.

show abstract

Section: Classic Methodsmentioning

confidence: 99%

InDiD: Instant Disorder Detection via Representation Learning

Romanenkova¹,

Stepikin²,

Morozov³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…The computing robustness, fault tolerant nature, scalability and reduced consumption footprint are among the key characteristics that made this fruitful technology become popular in recent research works. The investigations aim to develop effective SC-based architectures that can be beneficially applied in image processing algorithms [3], [4], [5], [6], general purpose digital filter structures [7], [8], [9], [10], error correction hardware solutions [11], and artificial neural networks (ANNs) [12]. The cost of the aforementioned attributes is a trade-off between precision and latency in signal representations, since the longer the processed bit stream the higher precision is achieved.…”

Section: A Related Workmentioning

confidence: 99%

“…(1) indicates, the statistical average of the binary stream gives the estimation of the signal x (i.e., the estimation of the generating probability, sincep =x), thus the longer stream is processed, the better accuracy is obtained (x = x only if N → ∞). The accuracy of estimation is defined by its variance; it is considered as a coding noise that decreases by time [3], [17], [18]:…”

Section: A Stochastic Representationmentioning

confidence: 99%

A Stochastic Logic-Based Fuzzy Logic Controller: First Experimental Results of a Novel Architecture

2021

View full text Add to dashboard Cite

In stochastic computing (SC) systems numbers are represented with mean values of random binary sequences. This paper introduces a novel fuzzy inference architecture, in which the computational mechanism is based on stochastic logic (SL). First, the basic concept of SL is described, then the architecture of the SL-based fuzzy logic controller (SFLC) is built up systematically using the derived stochastic elements. The second part of the paper demonstrates the application of the proposed techniques, where the SFLC-based control performance is evaluated on a real mechatronic system. The results show that the SL-based approach provides effective and robust control performance, simple architecture and high noise tolerance. The proposed method is also benchmarked against conventional FLCs indicating that the robustness of the stochastic architecture allowed to outperform the benchmark controllers in noisy environments.INDEX TERMS stochastic logic, fuzzy logic controller, fuzzy hardware, self-balancing robot.

show abstract

RETRACTED: Development of cultural tourism platform based on FPGA and convolutional neural network

Yin

2021

Microprocessors and Microsystems

View full text Add to dashboard Cite

An FPGA multiprocessor architecture for Bayesian online change point detection using stochastic computation

Cited by 4 publications

References 12 publications

InDiD: Instant Disorder Detection via Representation Learning

InDiD: Instant Disorder Detection via Representation Learning

A Stochastic Logic-Based Fuzzy Logic Controller: First Experimental Results of a Novel Architecture

RETRACTED: Development of cultural tourism platform based on FPGA and convolutional neural network

Contact Info

Product

Resources

About