Browse
Submit Data
Databases
API
Help

Dataset Information

0 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Feature Representations for Neuromorphic Audio Spike Streams.

ABSTRACT: Event-driven neuromorphic spiking sensors such as the silicon retina and the silicon cochlea encode the external sensory stimuli as asynchronous streams of spikes across different channels or pixels. Combining state-of-art deep neural networks with the asynchronous outputs of these sensors has produced encouraging results on some datasets but remains challenging. While the lack of effective spiking networks to process the spike streams is one reason, the other reason is that the pre-processing methods required to convert the spike streams to frame-based features needed for the deep networks still require further investigation. This work investigates the effectiveness of synchronous and asynchronous frame-based features generated using spike count and constant event binning in combination with the use of a recurrent neural network for solving a classification task using N-TIDIGITS18 dataset. This spike-based dataset consists of recordings from the Dynamic Audio Sensor, a spiking silicon cochlea sensor, in response to the TIDIGITS audio dataset. We also propose a new pre-processing method which applies an exponential kernel on the output cochlea spikes so that the interspike timing information is better preserved. The results from the N-TIDIGITS18 dataset show that the exponential features perform better than the spike count features, with over 91% accuracy on the digit classification task. This accuracy corresponds to an improvement of at least 2.5% over the use of spike count features, establishing a new state of the art for this dataset.

SUBMITTER: Anumula J

PROVIDER: S-EPMC5811520 | biostudies-other | 2018

REPOSITORIES: biostudies-other

ACCESS DATA

Json Xml

Similar Datasets

A Spike-Based Neuromorphic Architecture of Stereo Vision.

Project description:The problem of finding stereo correspondences in binocular vision is solved effortlessly in nature and yet it is still a critical bottleneck for artificial machine vision systems. As temporal information is a crucial feature in this process, the advent of event-based vision sensors and dedicated event-based processors promises to offer an effective approach to solving the stereo matching problem. Indeed, event-based neuromorphic hardware provides an optimal substrate for fast, asynchronous computation, that can make explicit use of precise temporal coincidences. However, although several biologically-inspired solutions have already been proposed, the performance benefits of combining event-based sensing with asynchronous and parallel computation are yet to be explored. Here we present a hardware spike-based stereo-vision system that leverages the advantages of brain-inspired neuromorphic computing by interfacing two event-based vision sensors to an event-based mixed-signal analog/digital neuromorphic processor. We describe a prototype interface designed to enable the emulation of a stereo-vision system on neuromorphic hardware and we quantify the stereo matching performance with two datasets. Our results provide a path toward the realization of low-latency, end-to-end event-based, neuromorphic architectures for stereo vision.

| S-EPMC7693562 | biostudies-literature

Skimming Digits: Neuromorphic Classification of Spike-Encoded Images.

Project description:The growing demands placed upon the field of computer vision have renewed the focus on alternative visual scene representations and processing paradigms. Silicon retinea provide an alternative means of imaging the visual environment, and produce frame-free spatio-temporal data. This paper presents an investigation into event-based digit classification using N-MNIST, a neuromorphic dataset created with a silicon retina, and the Synaptic Kernel Inverse Method (SKIM), a learning method based on principles of dendritic computation. As this work represents the first large-scale and multi-class classification task performed using the SKIM network, it explores different training patterns and output determination methods necessary to extend the original SKIM method to support multi-class problems. Making use of SKIM networks applied to real-world datasets, implementing the largest hidden layer sizes and simultaneously training the largest number of output neurons, the classification system achieved a best-case accuracy of 92.87% for a network containing 10,000 hidden layer neurons. These results represent the highest accuracies achieved against the dataset to date and serve to validate the application of the SKIM method to event-based visual classification tasks. Additionally, the study found that using a square pulse as the supervisory training signal produced the highest accuracy for most output determination methods, but the results also demonstrate that an exponential pattern is better suited to hardware implementations as it makes use of the simplest output determination method based on the maximum value.

| S-EPMC4848313 | biostudies-literature

Reconstruction of audio waveforms from spike trains of artificial cochlea models.

Project description:Spiking cochlea models describe the analog processing and spike generation process within the biological cochlea. Reconstructing the audio input from the artificial cochlea spikes is therefore useful for understanding the fidelity of the information preserved in the spikes. The reconstruction process is challenging particularly for spikes from the mixed signal (analog/digital) integrated circuit (IC) cochleas because of multiple non-linearities in the model and the additional variance caused by random transistor mismatch. This work proposes an offline method for reconstructing the audio input from spike responses of both a particular spike-based hardware model called the AEREAR2 cochlea and an equivalent software cochlea model. This method was previously used to reconstruct the auditory stimulus based on the peri-stimulus histogram of spike responses recorded in the ferret auditory cortex. The reconstructed audio from the hardware cochlea is evaluated against an analogous software model using objective measures of speech quality and intelligibility; and further tested in a word recognition task. The reconstructed audio under low signal-to-noise (SNR) conditions (SNR < -5 dB) gives a better classification performance than the original SNR input in this word recognition task.

| S-EPMC4602092 | biostudies-literature

Neurophysiological mechanisms underlying motor feature binding processes and representations.

Project description:Coherent, voluntary action requires an integrated representation of these actions and their defining features. Although theories delineate how action integration requiring binding between different action features may be accomplished, the underlying neurophysiological mechanisms are largely elusive. The present study examined the neurophysiological mechanisms underlying binding processes in actions. To this end, we conducted EEG recordings and applied standard event-related potential analyses, temporal EEG signal decomposition and multivariate pattern analyses (MVPA). According to the code occupation account, an overlap between a planned and a to-be-performed action impairs performance. The level, to which performance is attenuated depends on the strength of binding of action features. This binding process then determines the representation of them, the so-called action files. We show that code occupation and bindings between action features specifically modulate processes preceding motor execution as showed by the stimulus-locked lateralized readiness potential (LRP). Conversely, motor execution processes reflected by the response-locked LRP were not modulated by action file binding. The temporal decomposition of the EEG signal, further distinguished between action file related processes: the planned response determining code occupation was reflected in general (voluntary) response selection but not in involuntary (response priming-related) activation. Moreover, MVPA on temporally decomposed neural signals indicated that action files are represented as a continuous chain of activations. Within this chain, inhibitory and response re-activation patterns can be distinguished. Taken together, the neurophysiological correlates of action file binding suggest that parallel, stimulus- and response-related pre-motor processes are responsible for the code occupation in the human motor system.

| S-EPMC7927300 | biostudies-literature

Inhibition decorrelates visual feature representations in the inner retina.

Project description:The retina extracts visual features for transmission to the brain. Different types of bipolar cell split the photoreceptor input into parallel channels and provide the excitatory drive for downstream visual circuits. Mouse bipolar cell types have been described at great anatomical and genetic detail, but a similarly deep understanding of their functional diversity is lacking. Here, by imaging light-driven glutamate release from more than 13,000 bipolar cell axon terminals in the intact retina, we show that bipolar cell functional diversity is generated by the interplay of dendritic excitatory inputs and axonal inhibitory inputs. The resulting centre and surround components of bipolar cell receptive fields interact to decorrelate bipolar cell output in the spatial and temporal domains. Our findings highlight the importance of inhibitory circuits in generating functionally diverse excitatory pathways and suggest that decorrelation of parallel visual pathways begins as early as the second synapse of the mouse visual system.

| S-EPMC5325673 | biostudies-literature

A biophysically-based neuromorphic model of spike rate- and timing-dependent plasticity.

Project description:Current advances in neuromorphic engineering have made it possible to emulate complex neuronal ion channel and intracellular ionic dynamics in real time using highly compact and power-efficient complementary metal-oxide-semiconductor (CMOS) analog very-large-scale-integrated circuit technology. Recently, there has been growing interest in the neuromorphic emulation of the spike-timing-dependent plasticity (STDP) Hebbian learning rule by phenomenological modeling using CMOS, memristor or other analog devices. Here, we propose a CMOS circuit implementation of a biophysically grounded neuromorphic (iono-neuromorphic) model of synaptic plasticity that is capable of capturing both the spike rate-dependent plasticity (SRDP, of the Bienenstock-Cooper-Munro or BCM type) and STDP rules. The iono-neuromorphic model reproduces bidirectional synaptic changes with NMDA receptor-dependent and intracellular calcium-mediated long-term potentiation or long-term depression assuming retrograde endocannabinoid signaling as a second coincidence detector. Changes in excitatory or inhibitory synaptic weights are registered and stored in a nonvolatile and compact digital format analogous to the discrete insertion and removal of AMPA or GABA receptor channels. The versatile Hebbian synapse device is applicable to a variety of neuroprosthesis, brain-machine interface, neurorobotics, neuromimetic computation, machine learning, and neural-inspired adaptive control problems.

| S-EPMC3241759 | biostudies-literature

Uncovering representations of sleep-associated hippocampal ensemble spike activity.

Project description:Pyramidal neurons in the rodent hippocampus exhibit spatial tuning during spatial navigation, and they are reactivated in specific temporal order during sharp-wave ripples observed in quiet wakefulness or slow wave sleep. However, analyzing representations of sleep-associated hippocampal ensemble spike activity remains a great challenge. In contrast to wake, during sleep there is a complete absence of animal behavior, and the ensemble spike activity is sparse (low occurrence) and fragmental in time. To examine important issues encountered in sleep data analysis, we constructed synthetic sleep-like hippocampal spike data (short epochs, sparse and sporadic firing, compressed timescale) for detailed investigations. Based upon two Bayesian population-decoding methods (one receptive field-based, and the other not), we systematically investigated their representation power and detection reliability. Notably, the receptive-field-free decoding method was found to be well-tuned for hippocampal ensemble spike data in slow wave sleep (SWS), even in the absence of prior behavioral measure or ground truth. Our results showed that in addition to the sample length, bin size, and firing rate, number of active hippocampal pyramidal neurons are critical for reliable representation of the space as well as for detection of spatiotemporal reactivated patterns in SWS or quiet wakefulness.

| S-EPMC5004124 | biostudies-literature

Mosaic: in-memory computing and routing for small-world spike-based neuromorphic systems.

Project description:The brain's connectivity is locally dense and globally sparse, forming a small-world graph-a principle prevalent in the evolution of various species, suggesting a universal solution for efficient information routing. However, current artificial neural network circuit architectures do not fully embrace small-world neural network models. Here, we present the neuromorphic Mosaic: a non-von Neumann systolic architecture employing distributed memristors for in-memory computing and in-memory routing, efficiently implementing small-world graph topologies for Spiking Neural Networks (SNNs). We've designed, fabricated, and experimentally demonstrated the Mosaic's building blocks, using integrated memristors with 130 nm CMOS technology. We show that thanks to enforcing locality in the connectivity, routing efficiency of Mosaic is at least one order of magnitude higher than other SNN hardware platforms. This is while Mosaic achieves a competitive accuracy in a variety of edge benchmarks. Mosaic offers a scalable approach for edge systems based on distributed spike-based computing and in-memory routing.

| S-EPMC10761708 | biostudies-literature

Feature- and order-based timing representations in the frontal cortex.

Project description:We examined activity in the frontal cortex as monkeys performed a duration-discrimination task. Two stimuli, one red and the other blue, appeared sequentially on a video screen--in either order. Later, both stimuli reappeared, and to receive a reward the monkeys had to choose the stimulus that had lasted longer during its initial presentation. Some neurons encoded stimulus duration, but a larger number of cells represented their relative duration, which was encoded in three ways: whether the first or second stimulus had lasted longer; whether the red or blue stimulus had lasted longer; or, less commonly, as the difference between the two durations. As the monkeys' choice approached, the signal encoding which stimulus (red or blue) had lasted longer increased as the order-based signal dissipated. By representing stimulus durations and relative durations--both bound to stimulus features and event order--the frontal cortex could contribute to both temporal perception and episodic memory.

| S-EPMC2803114 | biostudies-literature

Feature-based representations of emotional facial expressions in the human amygdala.

Project description:The amygdala plays a central role in processing facial affect, responding to diverse expressions and features shared between expressions. Although speculation exists regarding the nature of relationships between expression- and feature-specific amygdala reactivity, this matter has not been fully explored. We used functional magnetic resonance imaging and principal component analysis (PCA) in a sample of 300 young adults, to investigate patterns related to expression- and feature-specific amygdala reactivity to faces displaying neutral, fearful, angry or surprised expressions. The PCA revealed a two-dimensional correlation structure that distinguished emotional categories. The first principal component separated neutral and surprised from fearful and angry expressions, whereas the second principal component separated neutral and angry from fearful and surprised expressions. This two-dimensional correlation structure of amygdala reactivity may represent specific feature-based cues conserved across discrete expressions. To delineate which feature-based cues characterized this pattern, face stimuli were averaged and then subtracted according to their principal component loadings. The first principal component corresponded to displacement of the eyebrows, whereas the second principal component corresponded to increased exposure of eye whites together with movement of the brow. Our results suggest a convergent representation of facial affect in the amygdala reflecting feature-based processing of discrete expressions.

| S-EPMC4158364 | biostudies-literature

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data