A Novel Quantum-Inspired Fuzzy Based Neural Network for Data Classification

Patel, Om Prakash; Bharill, Neha; Tiwari, Aruna; Prasad, Mukesh

doi:10.1109/tetc.2019.2901272

Cited by 29 publications

(14 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The quantum-inspired algorithms are not specific to fuzzy systems, as it also exists for some other computational intelligence methods, e.g. quantum-inspired genetic algorithm [18], quantum fuzzy C-means data clustering [19] and quantuminspired neuro-fuzzy systems [20]. Some other research works around quantum-inspired computational intelligence are comprehensively reviewed in [21].…”

Section: Related Workmentioning

confidence: 99%

Fuzzy Logic on Quantum Annealers

Pourabdollah

Schiattarella

2022

IEEE Trans. Fuzzy Syst.

View full text Add to dashboard Cite

Quantum computation is going to revolutionize the world of computing by enabling the design of massive parallel algorithms that solve hard problems in an efficient way, thanks to the exploitation of quantum mechanics effects, such as superposition, entanglement and interference. These computational improvements could strongly influence the way how fuzzy systems are designed and used in contexts, such as big data, where computational efficiency represents a non-negligible constraint to be taken into account. In order to pave the way towards this innovative scenario, this paper introduces a novel representation of fuzzy sets and operators based on Quadratic Unconstrained Binary Optimization (QUBO) problems, so as to enable the implementation of fuzzy inference engines on a type of quantum computers known as quantum annealers.

show abstract

Section: Related Workmentioning

confidence: 99%

Fuzzy Logic on Quantum Annealers

Pourabdollah

Schiattarella

2022

IEEE Trans. Fuzzy Syst.

View full text Add to dashboard Cite

show abstract

“…1) Conventional Stochastic Divider: Figure 5 illustrates a conventional bipolar divider. The feedback is constructed as per the comparison between the values of p(x) • p(y) and p(x) 2 • p(y) p(x) ; so, there are three multipliers (i.e., XNOR gates) in the divider circuit. The probability of the counter is initially set to 0 (in the bipolar representation), and the quotient is calculated once the feedback is stable.…”

Section: B Stochastic Dividersmentioning

confidence: 99%

“…A RTIFICIAL Neural Networks (ANNs) are some of the most widely used machine learning hardware systems to perform for example classification tasks over a wide range of applications [1], [2]. Among ANNs used in todays' machine learning, the Multi-Layer Perceptron (MLP) is the simplest but still powerful type [3].…”

Section: Introductionmentioning

confidence: 99%

Stochastic Dividers for Low Latency Neural Networks

Liu

Tang

Niknia

et al. 2021

IEEE Trans. Circuits Syst. I

View full text Add to dashboard Cite

Due to the low complexity in arithmetic unit design, stochastic computing (SC) has attracted considerable interest to implement Artificial Neural Networks (ANNs) for resourceslimited applications, because ANNs must usually perform a large number of arithmetic operations. To attain a high computation accuracy in an SC-based ANN, extended stochastic logic is utilized together with standard SC units and thus, a stochastic divider is required to perform the conversion between these logic representations. However, the conventional divider incurs in a large computation latency, so limits an SC implementation for ANNs used in applications needing high performance. Therefore, there is a need to design fast stochastic dividers for SC-based ANNs. Recent works (e.g., a binary searching and triple modular redundancy (BS-TMR) based stochastic divider) are targeting a reduction in computation latency, while keeping the same accuracy compared with the traditional design. However, this divider still requires N iterations to deal with 2 N -bit stochastic sequences, and thus the latency increases in proportion to the sequence length. In this paper, a decimal searching and TMR (DS-TMR) based stochastic divider is initially proposed to further reduce the computation latency; it only requires two iterations to calculate the quotient, so regardless of the sequence length. Moreover, a trade-off design between accuracy and hardware is also presented. An SC-based Multi-Layer Perceptron (MLP) is then considered to show the effectiveness of the proposed dividers over current designs. Results show that when utilizing the proposed dividers, the MLP achieves the lowest computation Manuscript

show abstract

“…The work in [40] proposed a novel fuzzy rule transfer mechanism for constructing fuzzy inference neural networks to perform two-class classification, such as what happens in financial forecasting (e.g., buy or sell). Finally, the authors in [41] proposed a novel learning model, called the Quantum-inspired Fuzzy Based Neural Network, for classification. This learning happens using concepts of Fuzzy c-Means clustering.…”

Section: Background and Related Workmentioning

confidence: 99%

A Holistic Auto-Configurable Ensemble Machine Learning Strategy for Financial Trading

et al. 2019

View full text Add to dashboard Cite

Financial markets forecasting represents a challenging task for a series of reasons, such as the irregularity, high fluctuation, noise of the involved data, and the peculiar high unpredictability of the financial domain. Moreover, literature does not offer a proper methodology to systematically identify intrinsic and hyper-parameters, input features, and base algorithms of a forecasting strategy in order to automatically adapt itself to the chosen market. To tackle these issues, this paper introduces a fully automated optimized ensemble approach, where an optimized feature selection process has been combined with an automatic ensemble machine learning strategy, created by a set of classifiers with intrinsic and hyper-parameters learned in each marked under consideration. A series of experiments performed on different real-world futures markets demonstrate the effectiveness of such an approach with regard to both to the Buy and Hold baseline strategy and to several canonical state-of-the-art solutions.

show abstract

A Novel Quantum-Inspired Fuzzy Based Neural Network for Data Classification

Cited by 29 publications

References 41 publications

Fuzzy Logic on Quantum Annealers

Fuzzy Logic on Quantum Annealers

Stochastic Dividers for Low Latency Neural Networks

A Holistic Auto-Configurable Ensemble Machine Learning Strategy for Financial Trading

Contact Info

Product

Resources

About