Recurrent Neural Networks (RNNs) are useful in temporal sequence tasks. However, training RNNs involves dense matrix multiplications which require hardware that can support a large number of arithmetic operations and memory accesses. Implementing online training of RNNs on the edge calls for optimized algorithms for an efficient deployment on hardware. Inspired by the spiking neuron model, the Delta RNN exploits temporal sparsity during inference by skipping over the update of hidden states from those inactivated neurons whose change of activation across two timesteps is below a defined threshold. This work describes a training algorithm for Delta RNNs that exploits temporal sparsity in the backward propagation phase to reduce computational requirements for training on the edge. Due to the symmetric computation graphs of forward and backward propagation during training, the gradient computation of inactivated neurons can be skipped. Results show a reduction of $\sim$80% in matrix operations for training a 56k parameter Delta LSTM on the Fluent Speech Commands dataset with negligible accuracy loss. Logic simulations of a hardware accelerator designed for the training algorithm show 2-10X speedup in matrix computations for an activation sparsity range of 50%-90%. Additionally, we show that the proposed Delta RNN training will be useful for online incremental learning on edge devices with limited computing resources.
Dynamic Vision Sensors (DVS) record "events" corresponding to pixel-level brightness changes, resulting in data-efficient representation of a dynamic visual scene. As DVS expand into increasingly diverse applications, non-ideal behaviors in their output under extreme sensing conditions are important to consider. Under low illumination (below ~10 lux) their output begins to be dominated by shot noise events (SNEs) which increase the data output and obscure true signal. SNE rates can be controlled to some degree by tuning circuit parameters to reduce sensitivity or temporal response bandwidth at the cost of signal loss. Alternatively, an improved understanding of SNE statistics can be leveraged to develop novel techniques for minimizing uninformative sensor output. We first explain a fundamental observation about sequential pairing of opposite polarity SNEs based on pixel circuit logic and validate our theory using DVS recordings and simulations. Finally, we derive a practical result from this new understanding and demonstrate two novel biasing techniques to reduce SNEs by 50% and 80% respectively while still retaining sensitivity and/or temporal resolution.
This article presents the first keyword spotting (KWS) IC which uses a ring-oscillator-based time-domain processing technique for its analog feature extractor (FEx). Its extensive usage of time-encoding schemes allows the analog audio signal to be processed in a fully time-domain manner except for the voltage-to-time conversion stage of the analog front-end. Benefiting from fundamental building blocks based on digital logic gates, it offers a better technology scalability compared to conventional voltage-domain designs. Fabricated in a 65 nm CMOS process, the prototyped KWS IC occupies 2.03mm$^{2}$ and dissipates 23 $\mu$W power consumption including analog FEx and digital neural network classifier. The 16-channel time-domain FEx achieves 54.89 dB dynamic range for 16 ms frame shift size while consuming 9.3 $\mu$W. The measurement result verifies that the proposed IC performs a 12-class KWS task on the Google Speech Command Dataset (GSCD) with >86% accuracy and 12.4 ms latency.
Standard dynamic vision sensor (DVS) event cameras output a stream of spatially-independent log-intensity brightness change events so they cannot suppress spatial redundancy. Nearly all biological retinas use an antagonistic center-surround organization. This paper proposes a practical method of implementing a compact, energy-efficient Center Surround DVS (CSDVS) with a surround smoothing network that uses compact polysilicon resistors for lateral resistance. The paper includes behavioral simulation results for the CSDVS (see sites.google.com/view/csdvs/home). The CSDVS would significantly reduce events caused by low spatial frequencies, but amplify the informative high frequency spatiotemporal events.
The stomatopod (mantis shrimp) visual system has recently provided a blueprint for the design of paradigm-shifting polarization and multispectral imaging sensors, enabling solutions to challenging medical and remote sensing problems. However, these bioinspired sensors lack the high dynamic range (HDR) and asynchronous polarization vision capabilities of the stomatopod visual system, limiting temporal resolution to \~12 ms and dynamic range to \~ 72 dB. Here we present a novel stomatopod-inspired polarization camera which mimics the sustained and transient biological visual pathways to save power and sample data beyond the maximum Nyquist frame rate. This bio-inspired sensor simultaneously captures both synchronous intensity frames and asynchronous polarization brightness change information with sub-millisecond latencies over a million-fold range of illumination. Our PDAVIS camera is comprised of 346x260 pixels, organized in 2-by-2 macropixels, which filter the incoming light with four linear polarization filters offset by 45 degrees. Polarization information is reconstructed using both low cost and latency event-based algorithms and more accurate but slower deep neural networks. Our sensor is used to image HDR polarization scenes which vary at high speeds and to observe dynamical properties of single collagen fibers in bovine tendon under rapid cyclical loads
Long Short-Term Memory (LSTM) recurrent networks are frequently used for tasks involving time-sequential data such as speech recognition. However, it is difficult to deploy these networks on hardware to achieve high throughput and low latency because the fully connected structure makes LSTM networks a memory-bounded algorithm. Previous LSTM accelerators either exploited weight spatial sparsity or temporal activation sparsity. This paper proposes a new accelerator called "Spartus" that exploits spatio-temporal sparsity to achieve ultra-low latency inference. The spatial sparsity is induced using our proposed pruning method called Column-Balanced Targeted Dropout (CBTD), which structures sparse weight matrices for balanced workload. It achieved up to 96% weight sparsity with negligible accuracy difference for an LSTM network trained on a TIMIT phone recognition task. To induce temporal sparsity in LSTM, we create the DeltaLSTM by extending the previous DeltaGRU method to the LSTM network. This combined sparsity simultaneously saves on the weight memory access and associated arithmetic operations. Spartus was implemented on a Xilinx Zynq-7100 FPGA. The Spartus per-sample latency for a single DeltaLSTM layer of 1024 neurons averages 1 us. Spartus achieved 9.4 TOp/s effective batch-1 throughput and 1.1 TOp/J energy efficiency, which, respectively, are 4X and 7X higher than the previous state-of-the-art.
Dynamic vision sensor event cameras produce a variable data rate stream of brightness change events. Event production at the pixel level is controlled by threshold, bandwidth, and refractory period bias current parameter settings. Biases must be adjusted to match application requirements and the optimal settings depend on many factors. As a first step towards automatic control of biases, this paper proposes fixed-step feedback controllers that use measurements of event rate and noise. The controllers regulate the event rate within an acceptable range using threshold and refractory period control, and regulate noise using bandwidth control. Experiments demonstrate model validity and feedback control.
To help meet the increasing need for dynamic vision sensor (DVS) event camera data, we developed the v2e toolbox, which generates synthetic DVS event streams from intensity frame videos. Videos can be of any type, either real or synthetic. v2e optionally uses synthetic slow motion to upsample the video frame rate and then generates DVS events from these frames using a realistic pixel model that includes event threshold mismatch, finite illumination-dependent bandwidth, and several types of noise. v2e includes an algorithm that determines the DVS thresholds and bandwidth so that the synthetic event stream statistics match a given reference DVS recording. v2e is the first toolbox that can synthesize realistic low light DVS data. This paper also clarifies misleading claims about DVS characteristics in some of the computer vision literature. The v2e website is https://sites.google.com/view/video2events/home and code is hosted at https://github.com/SensorsINI/v2e.