Associative memory optimized method on deep neural networks for image classification

SSTE: Syllable-Specific Temporal Encoding to FORCE-learn audio sequences with an associative memory approach

The circuitry and pathways in the brains of humans and other species have long inspired researchers and system designers to develop accurate and efficient systems capable of solving real-world problems and responding in real-time. We propose the Syllable-Specific Temporal Encoding (SSTE) to learn vocal sequences in a reservoir of Izhikevich neurons, by forming associations between exclusive input activities and their corresponding syllables in the sequence. Our model converts the audio signals to cochleograms using the CAR-FAC model to simulate a brain-like auditory learning and memorization process. The reservoir is trained using a hardware-friendly approach to FORCE learning. Reservoir computing could yield associative memory dynamics with far less computational complexity compared to RNNs. The SSTE-based learning enables competent accuracy and stable recall of spatiotemporal sequences with fewer reservoir inputs compared with existing encodings in the literature for similar purpose, offering resource savings. The encoding points to syllable onsets and allows recalling from a desired point in the sequence, making it particularly suitable for recalling subsets of long vocal sequences. The SSTE demonstrates the capability of learning new signals without forgetting previously memorized sequences and displays robustness against occasional noise, a characteristic of real-world scenarios. The components of this model are configured to improve resource consumption and computational intensity, addressing some of the cost-efficiency issues that might arise in future implementations aiming for compactness and real-time, low-power operation. Overall, this model proposes a brain-inspired pattern generation network for vocal sequences that can be extended with other bio-inspired computations to explore their potentials for brain-like auditory perception. Future designs could inspire from this model to implement embedded devices that learn vocal sequences and recall them as needed in real-time. Such systems could acquire language and speech, operate as artificial assistants, and transcribe text to speech, in the presence of natural noise and corruption on audio data.

A High-Performance Anti-Noise Algorithm for Arrhythmia Recognition

In recent years, the incidence of cardiac arrhythmias has been on the rise because of changes in lifestyle and the aging population. Electrocardiograms (ECGs) are widely used for the automated diagnosis of cardiac arrhythmias. However, existing models possess poor noise robustness and complex structures, limiting their effectiveness. To solve these problems, this paper proposes an arrhythmia recognition system with excellent anti-noise performance: a convolutionally optimized broad learning system (COBLS). In the proposed COBLS method, the signal is convolved with blind source separation using a signal analysis method based on high-order-statistic independent component analysis (ICA). The constructed feature matrix is further feature-extracted and dimensionally reduced using principal component analysis (PCA), which reveals the essence of the signal. The linear feature correlation between the data can be effectively reduced, and redundant attributes can be eliminated to obtain a low-dimensional feature matrix that retains the essential features of the classification model. Then, arrhythmia recognition is realized by combining this matrix with the broad learning system (BLS). Subsequently, the model was evaluated using the MIT-BIH arrhythmia database and the MIT-BIH noise stress test database. The outcomes of the experiments demonstrate exceptional performance, with impressive achievements in terms of the overall accuracy, overall precision, overall sensitivity, and overall F1-score. Specifically, the results indicate outstanding performance, with figures reaching 99.11% for the overall accuracy, 96.95% for the overall precision, 89.71% for the overall sensitivity, and 93.01% for the overall F1-score across all four classification experiments. The model proposed in this paper shows excellent performance, with 24 dB, 18 dB, and 12 dB signal-to-noise ratios.

Multiple Mittag-Leffler Stability of Fractional-Order Complex-Valued Memristive Neural Networks With Delays

This article discusses the coexistence and dynamical behaviors of multiple equilibrium points (Eps) for fractional-order complex-valued memristive neural networks (FCVMNNs) with delays. First, based on the state space partition method, some sufficient conditions are proposed to guarantee that there are multiple Eps in one FCVMNN. Then, the Mittag-Leffler stability of those multiple Eps is proved by using the Lyapunov function. Simultaneously, the enlarged attraction basins are obtained to improve and extend the existing theoretical results in the previous literature. In addition, some existing stability results in the literature are special cases of a new result herein. Finally, two illustrative examples with computer simulations are presented to verify the effectiveness of theoretical analysis.

Multistability and associative memory of neural networks with Morita-like activation functions

This paper presents the multistability analysis and associative memory of neural networks (NNs) with Morita-like activation functions. In order to seek larger memory capacity, this paper proposes Morita-like activation functions. In a weakened condition, this paper shows that the NNs with n-neurons have (2m+1)ⁿ equilibrium points (Eps) and (m+1)ⁿ of them are locally exponentially stable, where the parameter m depends on the Morita-like activation functions, called Morita parameter. Also the attraction basins are estimated based on the state space partition. Moreover, this paper applies these NNs into associative memories (AMs). Compared with the previous related works, the number of Eps and AM's memory capacity are extensively increased. The simulation results are illustrated and some reliable associative memories examples are shown at the end of this paper.