Spiking neural networks (SNNs) well support spatio-temporal 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 unfolding 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 rate-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 feedforward and recurrent layers. Based upon challenging speech and image datasets including TI46, N-TIDIGITS, Fashion-MNIST and MNIST, ST-RSBP is able to train SNNs with an accuracy surpassing that of the current state-of-the-art SNN BP algorithms and conventional non-spiking deep learning models.
more »
« less
Knowledge Distillation between DNN and SNN for Intelligent Sensing Systems on Loihi Chip
Building accurate and efficient deep neural network (DNN) models for intelligent sensing systems to process data locally is essential. Spiking neural networks (SNNs) have gained significant popularity in recent years because they are more biological-plausible and energy-efficient than DNNs. However, SNNs usually have lower accuracy than DNNs. In this paper, we propose to use SNNs for image sensing applications. Moreover, we introduce the DNN-SNN knowledge distillation algorithm to reduce the accuracy gap between DNNs and SNNs. Our DNNSNN knowledge distillation improves the accuracy of an SNN by transferring knowledge between a DNN and an SNN. To better transfer the knowledge, our algorithm creates two learning paths from a DNN to an SNN. One path is between the output layer and another path is between the intermediate layer. DNNs use real numbers to propagate information between neurons while SNNs use 1-bit spikes. To empower the communication between DNNs and SNNs, we utilize a decoder to decode spikes into real numbers. Also, our algorithm creates a learning path from an SNN to a DNN. This learning path better adapts the DNN to the SNN by allowing the DNN to learn the knowledge from the SNN. Our SNN models are deployed on Loihi, which is a specialized chip for SNN models. On the MNIST dataset, our SNN models trained by the DNN-SNN knowledge distillation achieve better accuracy than the SNN models on GPU trained by other training algorithms with much lower energy consumption per image.
more »
« less
- Award ID(s):
- 1937487
- NSF-PAR ID:
- 10439793
- Date Published:
- Journal Name:
- 2023 24th International Symposium on Quality Electronic Design (ISQED)
- Page Range / eLocation ID:
- 1 to 8
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Spiking Neural Networks (SNN) are fast emerging as an alternative option to Deep Neural Networks (DNN). They are computationally more powerful and provide higher energy-efficiency than DNNs. While exciting at first glance, SNNs contain security-sensitive assets (e.g., neuron threshold voltage) and vulnerabilities (e.g., sensitivity of classification accuracy to neuron threshold voltage change) that can be exploited by the adversaries. We explore global fault injection attacks using external power supply and laser-induced local power glitches on SNN designed using common analog neurons to corrupt critical training parameters such as spike amplitude and neuron’s membrane threshold potential. We also analyze the impact of power-based attacks on the SNN for digit classification task and observe a worst-case classification accuracy degradation of −85.65%. We explore the impact of various design parameters of SNN (e.g., learning rate, spike trace decay constant, and number of neurons) and identify design choices for robust implementation of SNN. We recover classification accuracy degradation by 30–47% for a subset of power-based attacks by modifying SNN training parameters such as learning rate, trace decay constant, and neurons per layer. We also propose hardware-level defenses, e.g., a robust current driver design that is immune to power-oriented attacks, improved circuit sizing of neuron components to reduce/recover the adversarial accuracy degradation at the cost of negligible area, and 25% power overhead. We also propose a dummy neuron-based detection of voltage fault injection at ∼1% power and area overhead each.more » « less
-
Spiking neural network (SNN) has attracted more and more research attention due to its event-based property. SNNs are more power efficient with such property than a conventional artificial neural network. For transferring the information to spikes, SNNs need an encoding process. With the temporal encoding schemes, SNN can extract the temporal patterns from the original information. A more advanced encoding scheme is a multiplexing temporal encoding which combines several encoding schemes with different timescales to have a larger information density and dynamic range. After that, the spike timing dependence plasticity (STDP) learning algorithm is utilized for training the SNN since the SNN can not be trained with regular training algorithms like backpropagation. In this work, a spiking domain feature extraction neural network with temporal multiplexing encoding is designed on EAGLE and fabricated on the PCB board. The testbench’s power consumption is 400mW. From the test result, a conclusion can be drawn that the network on PCB can transfer the input information to multiplexing temporal encoded spikes and then utilize the spikes to adjust the synaptic weight voltage.more » « less
-
High-quality 3D image recognition is an important component of many vision and robotics systems. However, the accurate processing of these images requires the use of compute-expensive 3D Convolutional Neural Networks (CNNs). To address this challenge, we propose the use of Spiking Neural Networks (SNNs) that are generated from iso-architecture CNNs and trained with quantization-aware gradient descent to optimize their weights, membrane leak, and firing thresholds. During both training and inference, the analog pixel values of a 3D image are directly applied to the input layer of the SNN without the need to convert to a spike-train. This significantly reduces the training and inference latency and results in high degree of activation sparsity, which yields significant improvements in computational efficiency. However, this introduces energy-hungry digital multiplications in the first layer of our models, which we propose to mitigate using a processing-in-memory (PIM) architecture. To evaluate our proposal, we propose a 3D and a 3D/2D hybrid SNN-compatible convolutional architecture and choose hyperspectral imaging (HSI) as an application for 3D image recognition. We achieve overall test accuracy of 98.68, 99.50, and 97.95% with 5 time steps (inference latency) and 6-bit weight quantization on the Indian Pines, Pavia University, and Salinas Scene datasets, respectively. In particular, our models implemented using standard digital hardware achieved accuracies similar to state-of-the-art (SOTA) with ~560.6× and ~44.8× less average energy than an iso-architecture full-precision and 6-bit quantized CNN, respectively. Adopting the PIM architecture in the first layer, further improves the average energy, delay, and energy-delay-product (EDP) by 30, 7, and 38%, respectively.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
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/ISQED57927.2023.10129306
