Modeling the Dynamics of Spiking Networks with Memristor-Based STDP to Solve Classification Tasks

The problem with training spiking neural networks (SNNs) is relevant due to the ultra-low power consumption these networks could exhibit when implemented in neuromorphic hardware. The ongoing progress in the fabrication of memristors, a prospective basis for analogue synapses, gives relevance to studying the possibility of SNN learning on the base of synaptic plasticity models, obtained by fitting the experimental measurements of the memristor conductance change. The dynamics of memristor conductances is (necessarily) nonlinear, because conductance changes depend on the spike timings, which neurons emit in an all-or-none fashion. The ability to solve classification tasks was previously shown for spiking network models based on the bio-inspired local learning mechanism of spike-timing-dependent plasticity (STDP), as well as with the plasticity that models the conductance change of nanocomposite (NC) memristors. Input data were presented to the network encoded into the intensities of Poisson input spike sequences. This work considers another approach for encoding input data into input spike sequences presented to the network: temporal encoding, in which an input vector is transformed into relative timing of individual input spikes. Since temporal encoding uses fewer input spikes, the processing of each input vector by the network can be faster and more energy-efficient. The aim of the current work is to show the applicability of temporal encoding to training spiking networks with three synaptic plasticity models: STDP, NC memristor approximation, and PPX memristor approximation. We assess the accuracy of the proposed approach on several benchmark classification tasks: Fisher’s Iris, Wisconsin breast cancer, and the pole balancing task (CartPole). The accuracies achieved by SNN with memristor plasticity and conventional STDP are comparable and are on par with classic machine learning approaches.

¹²⁹Xe ultra-fast Z spectroscopy enables micromolar detection of biosensors on a 1 T benchtop spectrometer

The availability of a benchtop nuclear magnetic resonance (NMR) spectrometer, of low cost and easily transportable, can allow detection of low quantities of biosensors, provided that hyperpolarized species are used. Here we show that the micromolar threshold can easily be reached by employing laser-polarized xenon and cage molecules reversibly hosting it. Indirect detection of caged xenon is made via chemical exchange, using ultra-fast Z spectroscopy based on spatio-temporal encoding. On this non-dedicated low-field spectrometer, several ideas are proposed to improve the signal.

A novel 5D brain parcellation approach based on spatio-temporal encoding of resting fMRI data from deep residual learning

ObjectiveBrain parcellation is an essential aspect of computational neuroimaging research and deals with segmenting the brain into (possibly overlapping) sub-regions employed to study brain anatomy or function. In the context of functional parcellation, brain organization which is often measured via temporal metrics such as coherence, is highly dynamic. This dynamic aspect is ignored in most research, which typically applies anatomically based, fixed regions for each individual, and can produce misleading results.MethodsIn this work, we propose a novel spatio-temporal-network (5D) brain parcellation scheme utilizing a deep residual network to predict the probability of each voxel belonging to a brain network at each point in time.ResultsWe trained 53 4D brain networks and evaluate the ability of these networks to capture spatial and temporal dynamics as well as to show sensitivity to individual or group-level variation (in our case with age).ConclusionThe proposed system generates informative spatio-temporal networks that vary not only across individuals but also over time and space.SignificanceThe dynamic 5D nature of the developed approach provides a powerful framework that expands on existing work and has potential to identify novel and typically ignored findings when studying the healthy and disordered brain.

Attention-Based Temporal Encoding Network with Background-Independent Motion Mask for Action Recognition

Convolutional neural network (CNN) has been leaping forward in recent years. However, the high dimensionality, rich human dynamic characteristics, and various kinds of background interference increase difficulty for traditional CNNs in capturing complicated motion data in videos. A novel framework named the attention-based temporal encoding network (ATEN) with background-independent motion mask (BIMM) is proposed to achieve video action recognition here. Initially, we introduce one motion segmenting approach on the basis of boundary prior by associating with the minimal geodesic distance inside a weighted graph that is not directed. Then, we propose one dynamic contrast segmenting strategic procedure for segmenting the object that moves within complicated environments. Subsequently, we build the BIMM for enhancing the object that moves based on the suppression of the not relevant background inside the respective frame. Furthermore, we design one long-range attention system inside ATEN, capable of effectively remedying the dependency of sophisticated actions that are not periodic in a long term based on the more automatic focus on the semantical vital frames other than the equal process for overall sampled frames. For this reason, the attention mechanism is capable of suppressing the temporal redundancy and highlighting the discriminative frames. Lastly, the framework is assessed by using HMDB51 and UCF101 datasets. As revealed from the experimentally achieved results, our ATEN with BIMM gains 94.5% and 70.6% accuracy, respectively, which outperforms a number of existing methods on both datasets.

¹²⁹Xe Ultrafast Z-spectroscopy enables micromolar detection of biosensors on a 1T benchtop spectrometer

The availability of a benchtop NMR spectrometer, of low cost and easily transportable, can allow detection of low quantities of biosensors, provided that hyperpolarized species are used. Here we show that the micromolar threshold can easily be reached, by employing laser-polarized xenon and cage-molecules reversibly hosting it. Indirect detection of caged xenon is made via chemical exchange, using ultrafast Z-spectroscopy based on spatio-temporal encoding. On this non-dedicated low-field spectrometer, several ideas are proposed to improve the signal.