Brain-Inspired Spiking Neural Network Research Articles

Temporal-Sequential Learning With a Brain-Inspired Spiking Neural Network and Its Application to Musical Memory.

Sequence learning is a fundamental cognitive function of the brain. However, the ways in which sequential information is represented and memorized are not dealt with satisfactorily by existing models. To overcome this deficiency, this paper introduces a spiking neural network based on psychological and neurobiological findings at multiple scales. Compared with existing methods, our model has four novel features: (1) It contains several collaborative subnetworks similar to those in brain regions with different cognitive functions. The individual building blocks of the simulated areas are neural functional minicolumns composed of biologically plausible neurons. Both excitatory and inhibitory connections between neurons are modulated dynamically using a spike-timing-dependent plasticity learning rule. (2) Inspired by the mechanisms of the brain's cortical-striatal loop, a dependent timing module is constructed to encode temporal information, which is essential in sequence learning but has not been processed well by traditional algorithms. (3) Goal-based and episodic retrievals can be achieved at different time scales. (4) Musical memory is used as an application to validate the model. Experiments show that the model can store a huge amount of data on melodies and recall them with high accuracy. In addition, it can remember the entirety of a melody given only an episode or the melody played at different paces.

FPT-spike: a flexible precise-time-dependent single-spike neuromorphic computing architecture

Modern Artificial Neural networks (ANNs) like Convolutional Neural Network (CNN), have found broad applications in real-world cognitive tasks. One challenging faced by these models is their tremendous memory and computing resource requirement. This also greatly hinders their adoptions from resource-constraint platforms, such as drone, mobile phone and IoT devices. Recently the brain-inspired spiking neural network (SNN) has been demonstrated as a promising solution for delivering more impressive computing and power efficiency. For SNNs, a large body of prior work were conducted on the spiking system design with a focus on using the spike firing rate (or rate-coded) for fulfilling the practical cognitive tasks. Such rate-based designs can underestimate the energy efficiency, throughput and system flexibility of SNNs. On the other hand, the potentials of time-based SNN are not fully unleashed in real applications due to lack of efficient coding and practical learning schemes in temporal domain. In this work, we make an early attempt to fill this gap: that said, a flexible precise-time-dependent single-spike neuromorphic computing architecture, namely “FPT-Spike”, is developed. “FPT-spike” relies on three hardware-favorable components: precise ultra-sparse spike temporal encoding, efficient supervised temporal learning and fast asymmetric decoding, to realize flexible spatial–temporal information trade-off for neural network size reduction without scarifying data processing capability. Extensive experimental results show that “FPT-Spike” outperforms rate-based SNN and ANN significantly in three aspects: network size, processing speed and power consumption, demonstrating great potentials for its deployment in edge devices.

Application of a Brain-Inspired Spiking Neural Network Architecture to Odor Data Classification.

Existing methods in neuromorphic olfaction mainly focus on implementing the data transformation based on the neurobiological architecture of the olfactory pathway. While the transformation is pivotal for the sparse spike-based representation of odor data, classification techniques based on the bio-computations of the higher brain areas, which process the spiking data for identification of odor, remain largely unexplored. This paper argues that brain-inspired spiking neural networks constitute a promising approach for the next generation of machine intelligence for odor data processing. Inspired by principles of brain information processing, here we propose the first spiking neural network method and associated deep machine learning system for classification of odor data. The paper demonstrates that the proposed approach has several advantages when compared to the current state-of-the-art methods. Based on results obtained using a benchmark dataset, the model achieved a high classification accuracy for a large number of odors and has the capacity for incremental learning on new data. The paper explores different spike encoding algorithms and finds that the most suitable for the task is the step-wise encoding function. Further directions in the brain-inspired study of odor machine classification include investigation of more biologically plausible algorithms for mapping, learning, and interpretation of odor data along with the realization of these algorithms on some highly parallel and low power consuming neuromorphic hardware devices for real-world applications.

Deep learning and deep knowledge representation in Spiking Neural Networks for Brain-Computer Interfaces

Objective: This paper argues that Brain-Inspired Spiking Neural Network (BI-SNN) architectures can learn and reveal deep in time-space functional and structural patterns from spatio-temporal data. These patterns can be represented as deep knowledge, in a partial case in the form of deep spatio-temporal rules. This is a promising direction for building new types of Brain-Computer Interfaces called Brain-Inspired Brain–Computer Interfaces (BI-BCI). A theoretical framework and its experimental validation on deep knowledge extraction and representation using SNN are presented. Results: The proposed methodology was applied in a case study to extract deep knowledge of the functional and structural organisation of the brain’s neural network during the execution of a Grasp and Lift task. The BI-BCI successfully extracted the neural trajectories that represent the dorsal and ventral visual information processing streams as well as its connection to the motor cortex in the brain. Deep spatiotemporal rules on functional and structural interaction of distinct brain areas were then used for event prediction in BI-BCI. Significance: The computational framework can be used for unveiling the topological patterns of the brain and such knowledge can be effectively used to enhance the state-of-the-art in BCI.

Spiking Neural Network Modelling Approach Reveals How Mindfulness Training Rewires the Brain

There has been substantial interest in Mindfulness Training (MT) to understand how it can benefit healthy individuals as well as people with a broad range of health conditions. Research has begun to delineate associated changes in brain function. However, whether measures of brain function can be used to identify individuals who are more likely to respond to MT remains unclear. The present study applies a recently developed brain-inspired Spiking Neural Network (SNN) model to electroencephalography (EEG) data to provide novel insight into: i) brain function in depression; ii) the effect of MT on depressed and non-depressed individuals; and iii) neurobiological characteristics of depressed individuals who respond to mindfulness. Resting state EEG was recorded from before and after a 6 week MT programme in 18 participants. Based on self-report, 3 groups were formed: non-depressed (ND), depressed before but not after MT (responsive, D+) and depressed both before and after MT (unresponsive, D−). The proposed SNN, which utilises a standard brain-template, was used to model EEG data and assess connectivity, as indicated by activation levels across scalp regions (frontal, frontocentral, temporal, centroparietal and occipitoparietal), at baseline and follow-up. Results suggest an increase in activation following MT that was site-specific as a function of the group. Greater initial activation levels were seen in ND compared to depressed groups, and this difference was maintained at frontal and occipitoparietal regions following MT. At baseline, D+ had great activation than D−. Following MT, frontocentral and temporal activation reached ND levels in D+ but remained low in D−. Findings support the SNN approach in distinguishing brain states associated with depression and responsiveness to MT. The results also demonstrated that the SNN approach can be used to predict the effect of mindfulness on an individual basis before it is even applied.

Parameter Exploration to Improve Performance of Memristor-Based Neuromorphic Architectures

The brain-inspired spiking neural network neuromorphic architecture offers a promising solution for a wide set of cognitive computation tasks at a very low power consumption. Due to the practical feasibility of hardware implementation, we present a memristor-based model of hardware spiking neural networks which we simulate with Neural Network Scalable Spiking Simulator (N2S3), our open source neuromorphic architecture simulator. Although Spiking neural networks are widely used in the community of computational neuroscience and neuromorphic computation, there is still a need for research on the methods to choose the optimum parameters for better recognition efficiency. With the help of our simulator, we analyze and evaluate the impact of different parameters such as number of neurons, STDP window, neuron threshold, distribution of input spikes, and memristor model parameters on the MNIST hand-written digit recognition problem. We show that a careful choice of a few parameters (number of neurons, kind of synapse, STDP window, and neuron threshold) can significantly improve the recognition rate on this benchmark (around 15 points of improvement for the number of neurons, a few points for the others) with a variability of four to five points of recognition rate due to the random initialization of the synaptic weights.

Modelling Spiking Neural Network from the Architecture Evaluation Perspective

The brain-inspired spiking neural network (SNN) computing paradigm offers the potential for low-power and scalable computing, suited to many intelligent tasks that conventional computational systems find difficult. On the other hand, NoC (network-on-chips) based very large scale integration (VLSI) systems have been widely used to mimic neurobiological architectures (including SNNs). This paper proposes an evaluation methodology for SNN applications from the aspect of micro-architecture. First, we extract accurate SNN models from existing simulators of neural systems. Second, a cycle-accurate NoC simulator is implemented to execute the aforementioned SNN applications to get timing and energyconsumption information. We believe this method not only benefits the exploration of NoC design space but also bridges the gap between applications (especially those from the neuroscientists’ community) and neuromorphic hardware. Based on the method, we have evaluated some typical SNNs in terms of timing and energy. The method is valuable for the development of neuromorphic hardware and applications.

A brain-inspired spiking neural network model with temporal encoding and learning

Neural coding and learning are important components in cognitive memory system, by processing the sensory inputs and distinguishing different patterns to allow for higher level brain functions such as memory storage and retrieval. Benefitting from biological relevance, this paper presents a spiking neural network of leaky integrate-and-fire (LIF) neurons for pattern recognition. A biologically plausible supervised synaptic learning rule is used so that neurons can efficiently make a decision. The whole system contains encoding, learning and readout. Utilizing the temporal coding and learning, networks of spiking neurons can effectively and efficiently perform various classification tasks. It can classify complex patterns of activities stored in a vector, as well as the real-world stimuli. Our approach is also benchmarked on the nonlinearly separable Iris dataset. The proposed approach achieves a good generalization, with a classification accuracy of 99.63% for training and 92.55% for testing. In addition, the trained networks demonstrate that the temporal coding is a viable means for fast neural information processing.

EEG patterns during different emotions

Emotion recognition still poses a challenge lying at the core of the rapidly growing area of affective computing and is crucial for establishing a successful human–computer interaction. Identification and understanding of emotions are achieved through various measures, such as subjective self-reports, face-tracking, voice analysis, gaze-tracking, as well as the analysis of autonomic and central neurophysiological measurements. Current approaches to emotion recognition based on electroencephalography (EEG) mostly rely on various handcrafted features extracted over relatively long time windows of EEG during participants exposure to appropriate affective stimuli. In this paper, we present a short-term emotion recognition framework based on spiking neural network (SNN) modelling of spatio-temporal EEG patterns. Our method relies on EEG signal segmentation based on detection of short-term changes in facial landmarks, and as such includes no computation of handcrafted EEG features. Differences between participants’ EEG properties are taken into account via subject-dependent spike encoding in the formulated subject-independent emotion recognition task. We test our methods on the publicly available DEAP and MAHNOB-HCI databases due to the availability of both EEG and frontal face video data. Through an exhaustive hyperparameter optimisation strategy, we show that the proposed SNN-based representation of EEG spiking patterns provides valuable information for short- term emotion recognition. The obtained accuracies are 78.97% and 79.39% in arousal classification, and 67.76% and 72.12% in valence classification, on the DEAP and MAHNOB-HCI datasets, respectively. Furthermore, through the application of a brain-inspired SNN model, this study provides novel insight and helps in the understanding of the neural mechanisms involved in emotional processing in the context of audiovisual stimuli, such as affective videos. The presented results encourage the use of the proposed EEG processing methodology as a complement to existing features and methods commonly used for EEG-based emotion recognition, especially for short-term arousal recognition.