When Noise meets Chaos: Stochastic Resonance in Neurochaos Learning

Channel noise induced stochastic effect of Hodgkin-Huxley neurons in a real classification task

Noise is generally considered to have negative effects on information processing performance. However, it has also been proven that adding random noise or a certain level of stochastic (random) variability to a nonlinear system can increase its performance or sensitivity to weak signals. Despite the studies on this concept, called stochastic resonance in computational neuroscience, this phenomenon is still among the topics that need detailed research, especially in machine learning. In this study, the effect of noise arising from the intrinsic dynamics of the neurons forming the network in a spiking neural network consisting of Hodgkin-Huxley neurons on the image classification success of the network is investigated. In the first part of this two-part study, a practical neural network model consisting of Hodgkin-Huxley neurons is proposed and the network is tested in a 4-class real classification task. It is observed that the network consisting of Hodgkin-Huxley neurons has a classification performance at least as successful as the artificial neural network. In the second part of the study, the neurons in the network are replaced with stochastic Hodgkin-Huxley neurons, which more realistically represent the biological neuron, and the classification performance of the network at different cell membrane sizes is examined. Findings reveal that a spiking network consisting of stochastic Hodgkin-Huxley neurons, in which intrinsic noise dynamics are incorporated into the system, shows maximum classification performance at an optimal intrinsic noise level. It is called this reflection observed in the classification performance of a spiking network, which is referred to as stochastic resonance in computational neuroscience, as stochastic classification resonance in this study. This study also highlights the importance of bridging the gap between biological neuroscience and artificial neural networks for a better understanding of neurological structure.

Robust neural networks using stochastic resonance neurons

Various successful applications of deep artificial neural networks are effectively facilitated by the possibility to increase the number of layers and neurons in the network at the expense of the growing computational complexity. Increasing computational complexity to improve performance makes hardware implementation more difficult and directly affects both power consumption and the accumulation of signal processing latency, which are critical issues in many applications. Power consumption can be potentially reduced using analog neural networks, the performance of which, however, is limited by noise aggregation. Following the idea of physics-inspired machine learning, we propose here a type of neural network using stochastic resonances as a dynamic nonlinear node and demonstrate the possibility of considerably reducing the number of neurons required for a given prediction accuracy. We also observe that the performance of such neural networks is more robust against the impact of noise in the training data compared to conventional networks.

Predictive coding and stochastic resonance as fundamental principles of auditory phantom perception

Mechanistic insight is achieved only when experiments are employed to test formal or computational models. Furthermore, in analogy to lesion studies, phantom perception may serve as a vehicle to understand the fundamental processing principles underlying healthy auditory perception. With a special focus on tinnitus-as the prime example of auditory phantom perception-we review recent work at the intersection of artificial intelligence, psychology and neuroscience. In particular, we discuss why everyone with tinnitus suffers from (at least hidden) hearing loss, but not everyone with hearing loss suffers from tinnitus. We argue that intrinsic neural noise is generated and amplified along the auditory pathway as a compensatory mechanism to restore normal hearing based on adaptive stochastic resonance. The neural noise increase can then be misinterpreted as auditory input and perceived as tinnitus. This mechanism can be formalized in the Bayesian brain framework, where the percept (posterior) assimilates a prior prediction (brain's expectations) and likelihood (bottom-up neural signal). A higher mean and lower variance (i.e. enhanced precision) of the likelihood shifts the posterior, evincing a misinterpretation of sensory evidence, which may be further confounded by plastic changes in the brain that underwrite prior predictions. Hence, two fundamental processing principles provide the most explanatory power for the emergence of auditory phantom perceptions: predictive coding as a top-down and adaptive stochastic resonance as a complementary bottom-up mechanism. We conclude that both principles also play a crucial role in healthy auditory perception. Finally, in the context of neuroscience-inspired artificial intelligence, both processing principles may serve to improve contemporary machine learning techniques.

Design of a SIMO Deep Learning-Based Chaos Shift Keying (DLCSK) Communication System

This paper brings forward a Deep Learning (DL)-based Chaos Shift Keying (DLCSK) demodulation scheme to promote the capabilities of existing chaos-based wireless communication systems. In coherent Chaos Shift Keying (CSK) schemes, we need synchronization of chaotic sequences, which is still practically impossible in a disturbing environment. Moreover, the conventional Differential Chaos Shift Keying (DCSK) scheme has a drawback, that for each bit, half of the bit duration is spent sending non-information bearing reference samples. To deal with this drawback, a Long Short-Term Memory (LSTM)-based receiver is trained offline, using chaotic maps through a finite number of channel realizations, and then used for classifying online modulated signals. We presented that the proposed receiver can learn different chaotic maps and estimate channels implicitly, and then retrieves the transmitted messages without any need for chaos synchronization or reference signal transmissions. Simulation results for both the AWGN and Rayleigh fading channels show a remarkable BER performance improvement compared to the conventional DCSK scheme. The proposed DLCSK system will provide opportunities for a new class of receivers by leveraging the advantages of DL, such as effective serial and parallel connectivity. A Single Input Multiple Output (SIMO) architecture of the DLCSK receiver with excellent reliability is introduced to show its capabilities. The SIMO DLCSK benefits from a DL-based channel estimation approach, which makes this architecture simpler and more efficient for applications where channel estimation is problematic, such as massive MIMO, mmWave, and cloud-based communication systems.