Composing Recurrent Spiking Neural Networks using Locally-Recurrent Motifs and Risk-Mitigating Architectural Optimization

In neural circuits, recurrent connectivity plays a crucial role in network function and stability. However, existing recurrent spiking neural networks (RSNNs) are often constructed by random connections without optimization. While RSNNs can produce rich dynamics that are critical for memory formation and learning, systemic architectural optimization of RSNNs is still an opening challenge. We aim to enable systemic design of large RSNNs via a new scalable RSNN architecture and automated architectural optimization. We compose RSNNs based on a layer architecture called Sparsely-Connected Recurrent Motif Layer (SC-ML) that consists of multiple small recurrent motifs wired together by sparse lateral connections. The small size of the motifs and sparse inter-motif connectivity leads to an RSNN architecture scalable to large network sizes. We further propose a method called Hybrid Risk-Mitigating Architectural Search (HRMAS) to systematically optimize the topology of the proposed recurrent motifs and SC-ML layer architecture. HRMAS is an alternating two-step optimization process by which we mitigate the risk of network instability and performance degradation caused by architectural change by introducing a novel biologically-inspired self-repairing mechanism through intrinsic plasticity. The intrinsic plasticity is introduced to the second step of each HRMAS iteration and acts as unsupervised fast self-adaption to structural and synaptic weight modifications introduced by the first step during the RSNN architectural evolution. To the best of the authors knowledge, this is the first work that performs systematic architectural optimization of RSNNs. Using one speech and three neuromorphic datasets, we demonstrate the significant performance improvement brought by the proposed automated architecture optimization over existing manually-designed RSNNs.

Backpropagated Neighborhood Aggregation for Accurate Training of Spiking Neural Networks

While backpropagation (BP) has been applied to spiking neural networks (SNNs) achieving encouraging results, a key challenge involved is to backpropagate a continuous-valued loss over layers of spiking neurons exhibiting discontinuous all-or-none firing activities. Existing methods deal with this difficulty by introducing compromises that come with their own limitations, leading to potential performance degradation. We propose a novel BP-like method, called neighborhood aggregation (NA), which computes accurate error gradients guiding weight updates that may lead to discontinuous modifications of firing activities. NA achieves this goal by aggregating finite differences of the loss over multiple perturbed membrane potential waveforms in the neighborhood of the present membrane potential of each neuron while utilizing a new membrane potential distance function. Our experiments show that the proposed NA algorithm delivers the state-of-the-art performance for SNN training on several datasets.

Skip-Connected Self-Recurrent Spiking Neural Networks with Joint Intrinsic Parameter and Synaptic Weight Training

As an important class of spiking neural networks (SNNs), recurrent spiking neural networks (RSNNs) possess great computational power and have been widely used for processing sequential data like audio and text. However, most RSNNs suffer from two problems. 1. Due to a lack of architectural guidance, random recurrent connectivity is often adopted, which does not guarantee good performance. 2. Training of RSNNs is in general challenging, bottlenecking achievable model accuracy. To address these problems, we propose a new type of RSNNs called Skip-Connected Self-Recurrent SNNs (ScSr-SNNs). Recurrence in ScSr-SNNs is introduced in a stereotyped manner by adding self-recurrent connections to spiking neurons, which implements local memory. The network dynamics is enriched by skip connections between nonadjacent layers. Constructed by simplified self-recurrent and skip connections, ScSr-SNNs are able to realize recurrent behaviors similar to those of more complex RSNNs while the error gradients can be more straightforwardly calculated due to the mostly feedforward nature of the network. Moreover, we propose a new backpropagation (BP) method called backpropagated intrinsic plasticity (BIP) to further boost the performance of ScSr-SNNs by training intrinsic model parameters. Unlike standard intrinsic plasticity rules that adjust the neurons intrinsic parameters according to neuronal activity, the proposed BIP methods optimize intrinsic parameters based on the backpropagated error gradient of a well-defined global loss function in addition to synaptic weight training. Based upon challenging speech and neuromorphic speech datasets including TI46-Alpha, TI46-Digits, and N-TIDIGITS, the proposed ScSr-SNNs can boost performance by up to 2.55% compared with other types of RSNNs trained by state-of-the-art BP methods.

Unusual Electrical Conductivity Driven by Localized Stoichiometry Modification at Vertical Epitaxial Interfaces

Precise control of lattice mismatch accommodation and cation interdiffusion across the interface is critical to modulate correlated functionalities in epitaxial heterostructures, particularly when the interface composition is positioned near a compositional phase transition boundary. Here we select La1-xSrxMnO3 (LSMO) as a prototypical phase transition material and establish vertical epitaxial interfaces with NiO to explore the strong interplay between strain accommodation, stoichiometry modification, and localized electron transport across the interface. It is found that localized stoichiometry modification overcomes the plaguing dead layer problem in LSMO and leads to strongly directional conductivity, as manifested by more than three orders of magnitude difference between out-of-plane to in-plane conductivity. Comprehensive structural characterization and transport measurements reveal that this emerging behavior is related to a compositional change produced by directional cation diffusion that pushes the LSMO phase transition from insulating into metallic within an ultrathin interface region. This study explores the nature of unusual electric conductivity at vertical epitaxial interfaces and establishes an effective route for engineering nanoscale electron transport for oxide electronics.

Applying configurational complexity to the 2D Ruddlesden-Popper crystal structure

The 2D layered Ruddlesden-Popper crystal structure can host a broad range of functionally important behaviors. Here we establish extraordinary configurational disorder in a two dimensional layered Ruddlesden-Popper (RP) structure using entropy stabilization assisted synthesis. A protype A2CuO4 RP cuprate oxide with five components (La, Pr, Nd, Sm, Eu) on the A-site sublattice is designed and fabricated into epitaxial single crystal films using pulsed laser deposition. By comparing (La0.2Pr0.2Nd0.2Sm0.2Eu0.2)2CuO4 crystals grown under identical conditions but different substrates, it is found that heteroepitaxial strain plays an important role in crystal phase formation. When grown on a near lattice matched substrate, the high entropy oxide film features a T-type RP structure with uniform A-site cation mixing and square-planar CuO4 units, however, growing under strong compressive strain results in a single crystal non-RP cubic phase consistent with a CuX2O4 spinel structure. These observations are made with a range of combined characterizations using X-ray diffraction, atomic-resolution scanning transmission electron microscopy, energy-dispersive X-ray spectroscopy, and X-ray absorption spectroscopy measurements. Designing configurational complexity and moving between 2D layered RP and 3D cubic crystal structures in this class of cuprate materials opens many opportunities for new design strategies related to magnetoresistance, unconventional superconductivity, ferroelectricity, catalysis, and ion transport.

Temporal Spike Sequence Learning via Backpropagation for Deep Spiking Neural Networks

Spiking neural networks (SNNs) are well suited for spatio-temporal learning and implementations on energy-efficient event-driven neuromorphic processors. However, existing SNN error backpropagation (BP) methods lack proper handling of spiking discontinuities and suffer from low performance compared with the BP methods for traditional artificial neural networks. In addition, a large number of time steps are typically required to achieve decent performance, leading to high latency and rendering spike-based computation unscalable to deep architectures. We present a novel Temporal Spike Sequence Learning Backpropagation (TSSL-BP) method for training deep SNNs, which breaks down error backpropagation across two types of inter-neuron and intra-neuron dependencies and leads to improved temporal learning precision. It captures inter-neuron dependencies through presynaptic firing times by considering the all-or-none characteristics of firing activities and captures intra-neuron dependencies by handling the internal evolution of each neuronal state in time. TSSL-BP efficiently trains deep SNNs within a much shortened temporal window of a few steps while improving the accuracy for various image classification datasets including CIFAR10.

Boosting Throughput and Efficiency of Hardware Spiking Neural Accelerators using Time Compression Supporting Multiple Spike Codes

Spiking neural networks (SNNs) are the third generation of neural networks and can explore both rate and temporal coding for energy-efficient event-driven computation. However, the decision accuracy of existing SNN designs is contingent upon processing a large number of spikes over a long period. Nevertheless, the switching power of SNN hardware accelerators is proportional to the number of spikes processed while the length of spike trains limits throughput and static power efficiency. This paper presents the first study on developing temporal compression to significantly boost throughput and reduce energy dissipation of digital hardware SNN accelerators while being applicable to multiple spike codes. The proposed compression architectures consist of low-cost input spike compression units, novel input-and-output-weighted spiking neurons, and reconfigurable time constant scaling to support large and flexible time compression ratios. Our compression architectures can be transparently applied to any given pre-designed SNNs employing either rate or temporal codes while incurring minimal modification of the neural models, learning algorithms, and hardware design. Using spiking speech and image recognition datasets, we demonstrate the feasibility of supporting large time compression ratios of up to 16x, delivering up to 15.93x, 13.88x, and 86.21x improvements in throughput, energy dissipation, the tradeoffs between hardware area, runtime, energy, and classification accuracy, respectively based on different spike codes on a Xilinx Zynq-7000 FPGA. These results are achieved while incurring little extra hardware overhead.

Spike-Train Level Backpropagation for Training Deep Recurrent Spiking Neural Networks

Spiking neural networks (SNNs) well support spatiotemporal learning and energy-efficient event-driven hardware neuromorphic processors. As an important class of SNNs, recurrent spiking neural networks (RSNNs) possess great computational power. However, the practical application of RSNNs is severely limited by challenges in training. Biologically-inspired unsupervised learning has limited capability in boosting the performance of RSNNs. On the other hand, existing backpropagation (BP) methods suffer from high complexity of unrolling in time, vanishing and exploding gradients, and approximate differentiation of discontinuous spiking activities when applied to RSNNs. To enable supervised training of RSNNs under a well-defined loss function, we present a novel Spike-Train level RSNNs Backpropagation (ST-RSBP) algorithm for training deep RSNNs. The proposed ST-RSBP directly computes the gradient of a rated-coded loss function defined at the output layer of the network w.r.t tunable parameters. The scalability of ST-RSBP is achieved by the proposed spike-train level computation during which temporal effects of the SNN is captured in both the forward and backward pass of BP. Our ST-RSBP algorithm can be broadly applied to RSNNs with a single recurrent layer or deep RSNNs with multiple feed-forward and recurrent layers. Based upon challenging speech and image datasets including TI46, N-TIDIGITS, Fashion-MNIST and MNIST, ST-RSBP is able to train RSNNs with an accuracy surpassing that of the current state-of-art SNN BP algorithms and conventional non-spiking deep learning models.

Multiple Linear Regression Haze-removal Model Based on Dark Channel Prior

Dark Channel Prior (DCP) is a widely recognized traditional dehazing algorithm. However, it may fail in bright region and the brightness of the restored image is darker than hazy image. In this paper, we propose an effective method to optimize DCP. We build a multiple linear regression haze-removal model based on DCP atmospheric scattering model and train this model with RESIDE dataset, which aims to reduce the unexpected errors caused by the rough estimations of transmission map t(x) and atmospheric light A. The RESIDE dataset provides enough synthetic hazy images and their corresponding groundtruth images to train and test. We compare the performances of different dehazing algorithms in terms of two important full-reference metrics, the peak-signal-to-noise ratio (PSNR) as well as the structural similarity index measure (SSIM). The experiment results show that our model gets highest SSIM value and its PSNR value is also higher than most of state-of-the-art dehazing algorithms. Our results also overcome the weakness of DCP on real-world hazy images