Spiking Neural Networks (SNNs) are brain- inspired computing models incorporating unique temporal dynamics and event-driven processing. Rich dynamics in both space and time offer great challenges and opportunities for efficient processing of sparse spatiotemporal data compared with conventional artificial neural networks (ANNs). Specifically, the additional overheads for handling the added temporal dimension limit the computational capabilities of neuromorphic accelerators. Iterative processing at every time-point with sparse inputs in a temporally sequential manner not only degrades the utilization of the systolic array but also intensifies data movement.In this work, we propose a novel technique and architecture that significantly improve utilization and data movement while efficiently handling temporal sparsity of SNNs on systolic arrays. Unlike time-sequential processing in conventional SNN accelerators, we pack multiple time points into a single time window (TW) and process the computations induced by active synaptic inputs falling under several TWs in parallel, leading to the proposed parallel time batching. It allows weight reuse across multiple time points and enhances the utilization of the systolic array with reduced idling of processing elements, overcoming the irregularity of sparse firing activities. We optimize the granularity of time-domain processing, i.e., the TW size, which significantly impacts the data reuse and utilization. We further boost the utilization efficiency by simultaneously scheduling non-overlapping sparse spiking activities onto the array. The proposed architectures offer a unifying solution for general spiking neural networks with commonly exhibited temporal sparsity, a key challenge in hardware acceleration, delivering 248X energy-delay product (EDP) improvement on average compared to an SNN baseline for accelerating various networks. Compared to ANN based accelerators, our approach improves EDP by 47X on the CIFAR10 dataset.
more »
« less
This content will become publicly available on December 1, 2024
Landslide susceptibility modeling by interpretable neural network
Landslides are notoriously difficult to predict because numerous spatially and temporally varying factors contribute to slope stability. Artificial neural networks (ANN) have been shown to improve prediction accuracy but are largely uninterpretable. Here we introduce an additive ANN optimization framework to assess landslide susceptibility, as well as dataset division and outcome interpretation techniques. We refer to our approach, which features full interpretability, high accuracy, high generalizability and low model complexity, as superposable neural network (SNN) optimization. We validate our approach by training models on landslide inventories from three different easternmost Himalaya regions. Our SNN outperformed physically-based and statistical models and achieved similar performance to state-of-the-art deep neural networks. The SNN models found the product of slope and precipitation and hillslope aspect to be important primary contributors to high landslide susceptibility, which highlights the importance of strong slope-climate couplings, along with microclimates, on landslide occurrences.
more » « less- Award ID(s):
- 1945431
- NSF-PAR ID:
- 10476118
- Publisher / Repository:
- Communications earth & environment
- Date Published:
- Journal Name:
- Communications Earth & Environment
- Volume:
- 4
- Issue:
- 1
- ISSN:
- 2662-4435
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null (Ed.)Brain-inspired cognitive computing has so far followed two major approaches - one uses multi-layered artificial neural networks (ANNs) to perform pattern-recognition-related tasks, whereas the other uses spiking neural networks (SNNs) to emulate biological neurons in an attempt to be as efficient and fault-tolerant as the brain. While there has been considerable progress in the former area due to a combination of effective training algorithms and acceleration platforms, the latter is still in its infancy due to the lack of both. SNNs have a distinct advantage over their ANN counterparts in that they are capable of operating in an event-driven manner, thus consuming very low power. Several recent efforts have proposed various SNN hardware design alternatives, however, these designs still incur considerable energy overheads.In this context, this paper proposes a comprehensive design spanning across the device, circuit, architecture and algorithm levels to build an ultra low-power architecture for SNN and ANN inference. For this, we use spintronics-based magnetic tunnel junction (MTJ) devices that have been shown to function as both neuro-synaptic crossbars as well as thresholding neurons and can operate at ultra low voltage and current levels. Using this MTJ-based neuron model and synaptic connections, we design a low power chip that has the flexibility to be deployed for inference of SNNs, ANNs as well as a combination of SNN-ANN hybrid networks - a distinct advantage compared to prior works. We demonstrate the competitive performance and energy efficiency of the SNNs as well as hybrid models on a suite of workloads. Our evaluations show that the proposed design, NEBULA, is up to 7.9× more energy efficient than a state-of-the-art design, ISAAC, in the ANN mode. In the SNN mode, our design is about 45× more energy-efficient than a contemporary SNN architecture, INXS. Power comparison between NEBULA ANN and SNN modes indicates that the latter is at least 6.25× more power-efficient for the observed benchmarks.more » « less
-
: In order to evaluate urban earthquake resilience, reliable structural modeling is needed. However, detailed modeling of a large number of structures and carrying out time history analyses for sets of ground motions are not practical at an urban scale. Reduced-order surrogate models can expedite numerical simulations while maintaining necessary engineering accuracy. Neural networks have been shown to be a powerful tool for developing surrogate models, which often outperform classical surrogate models in terms of scalability of complex models. Training a reliable deep learning model, however, requires an immense amount of data that contain a rich input-output relationship, which typically cannot be satisfied in practical applications. In this paper, we propose model-informed symbolic neural networks (MiSNN) that can discover the underlying closed-form formulations (differential equations) for a reduced-order surrogate model. The MiSNN will be trained on datasets obtained from dynamic analyses of detailed reinforced concrete special moment frames designed for San Francisco, California, subject to a series of selected ground motions. Training the MiSNN is equivalent to finding the solution to a sparse optimization problem, which is solved by the Adam optimizer. The earthquake ground acceleration and story displacement, velocity, and acceleration time histories will be used to train 1) an integrated SNN, which takes displacement and velocity states and outputs the absolute acceleration response of the structure; and 2) a distributed SNN, which distills the underlying equation of motion for each story. The results show that the MiSNN can reduce computational cost while maintaining high prediction accuracy of building responses.more » « less
-
Spike train classification is an important problem in many areas such as healthcare and mobile sensing, where each spike train is a high-dimensional time series of binary values. Conventional re- search on spike train classification mainly focus on developing Spiking Neural Networks (SNNs) under resource-sufficient settings (e.g., on GPU servers). The neurons of the SNNs are usually densely connected in each layer. However, in many real-world applications, we often need to deploy the SNN models on resource-constrained platforms (e.g., mobile devices) to analyze high-dimensional spike train data. The high resource requirement of the densely-connected SNNs can make them hard to deploy on mobile devices. In this paper, we study the problem of energy-efficient SNNs with sparsely- connected neurons. We propose an SNN model with sparse spatiotemporal coding. Our solution is based on the re-parameterization of weights in an SNN and the application of sparsity regularization during optimization. We compare our work with the state-of-the-art SNNs and demonstrate that our sparse SNNs achieve significantly better computational efficiency on both neuromorphic and standard datasets with comparable classification accuracy. Furthermore, com- pared with densely-connected SNNs, we show that our method has a better capability of generalization on small-size datasets through extensive experiments.more » « less
-
null (Ed.)Spike train classification is an important problem in many areas such as healthcare and mobile sensing, where each spike train is a high-dimensional time series of binary values. Conventional re- search on spike train classification mainly focus on developing Spiking Neural Networks (SNNs) under resource-sufficient settings (e.g., on GPU servers). The neurons of the SNNs are usually densely connected in each layer. However, in many real-world applications, we often need to deploy the SNN models on resource-constrained platforms (e.g., mobile devices) to analyze high-dimensional spike train data. The high resource requirement of the densely-connected SNNs can make them hard to deploy on mobile devices. In this paper, we study the problem of energy-efficient SNNs with sparsely- connected neurons. We propose an SNN model with sparse spatio-temporal coding. Our solution is based on the re-parameterization of weights in an SNN and the application of sparsity regularization during optimization. We compare our work with the state-of-the-art SNNs and demonstrate that our sparse SNNs achieve significantly better computational efficiency on both neuromorphic and standard datasets with comparable classification accuracy. Furthermore, com- pared with densely-connected SNNs, we show that our method has a better capability of generalization on small-size datasets through extensive experiments.more » « less
