اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدCSB-RNN: A Faster-than-Realtime RNN Acceleration Framework with Compressed Structured Blocks
93
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Recurrent neural networks (RNNs) have been widely adopted in temporal sequence analysis, where realtime performance is often in demand. However, RNNs suffer from heavy computational workload as the model often comes with large weight matrices. Pruning schemes have been proposed for RNNs to eliminate the redundant (close-to-zero) weight values. On one hand, the non-structured pruning methods achieve a high pruning rate but introducing computation irregularity (random sparsity), which is unfriendly to parallel hardware. On the other hand, hardware-oriented structured pruning suffers from low pruning rate due to restricted constraints on allowable pruning structure. This paper presents CSB-RNN, an optimized full-stack RNN framework with a novel compressed structured block (CSB) pruning technique. The CSB pruned RNN model comes with both fine pruning granularity that facilitates a high pruning rate and regular structure that benefits the hardware parallelism. To address the challenges in parallelizing the CSB pruned model inference with fine-grained structural sparsity, we propose a novel hardware architecture with a dedicated compiler. Gaining from the architecture-compilation co-design, the hardware not only supports various RNN cell types, but is also able to address the challenging workload imbalance issue and therefore significantly improves the hardware efficiency.
قيم البحث
اقرأ أيضاً
Recurrent Neural Network (RNN) inference exhibits low hardware utilization due to the strict data dependencies across time-steps. Batching multiple requests can increase throughput. However, RNN batching requires a large amount of padding since the b
atched input sequences may largely differ in length. Schemes that dynamically update the batch every few time-steps avoid padding. However, they require executing different RNN layers in a short timespan, decreasing energy efficiency. Hence, we propose E-BATCH, a low-latency and energy-efficient batching scheme tailored to RNN accelerators. It consists of a runtime system and effective hardware support. The runtime concatenates multiple sequences to create large batches, resulting in substantial energy savings. Furthermore, the accelerator notifies it when the evaluation of a sequence is done, so that a new sequence can be immediately added to a batch, thus largely reducing the amount of padding. E-BATCH dynamically controls the number of time-steps evaluated per batch to achieve the best trade-off between latency and energy efficiency for the given hardware platform. We evaluate E-BATCH on top of E-PUR and TPU. In E-PUR, E-BATCH improves throughput by 1.8x and energy-efficiency by 3.6x, whereas in TPU, it improves throughput by 2.1x and energy-efficiency by 1.6x, over the state-of-the-art.
In this paper we propose mmFall - a novel fall detection system, which comprises of (i) the emerging millimeter-wave (mmWave) radar sensor to collect the human bodys point cloud along with the body centroid, and (ii) a variational recurrent autoencod
er (VRAE) to compute the anomaly level of the body motion based on the acquired point cloud. A fall is claimed to have occurred when the spike in anomaly level and the drop in centroid height occur simultaneously. The mmWave radar sensor provides several advantages, such as privacycompliance and high-sensitivity to motion, over the traditional sensing modalities. However, (i) randomness in radar point cloud data and (ii) difficulties in fall collection/labeling in the traditional supervised fall detection approaches are the two main challenges. To overcome the randomness in radar data, the proposed VRAE uses variational inference, a probabilistic approach rather than the traditional deterministic approach, to infer the posterior probability of the bodys latent motion state at each frame, followed by a recurrent neural network (RNN) to learn the temporal features of the motion over multiple frames. Moreover, to circumvent the difficulties in fall data collection/labeling, the VRAE is built upon an autoencoder architecture in a semi-supervised approach, and trained on only normal activities of daily living (ADL) such that in the inference stage the VRAE will generate a spike in the anomaly level once an abnormal motion, such as fall, occurs. During the experiment, we implemented the VRAE along with two other baselines, and tested on the dataset collected in an apartment. The receiver operating characteristic (ROC) curve indicates that our proposed model outperforms the other two baselines, and achieves 98% detection out of 50 falls at the expense of just 2 false alarms.
In this paper we examine learning methods combining the Random Neural Network, a biologically inspired neural network and the Extreme Learning Machine that achieve state of the art classification performance while requiring much shorter training time
. The Random Neural Network is a integrate and fire computational model of a neural network whose mathematical structure permits the efficient analysis of large ensembles of neurons. An activation function is derived from the RNN and used in an Extreme Learning Machine. We compare the performance of this combination against the ELM with various activation functions, we reduce the input dimensionality via PCA and compare its performance vs. autoencoder bas
Previous works on the Recurrent Neural Network-Transducer (RNN-T) models have shown that, under some conditions, it is possible to simplify its prediction network with little or no loss in recognition accuracy (arXiv:2003.07705 [eess.AS], [2], arXiv:
2012.06749 [cs.CL]). This is done by limiting the context size of previous labels and/or using a simpler architecture for its layers instead of LSTMs. The benefits of such changes include reduction in model size, faster inference and power savings, which are all useful for on-device applications. In this work, we study ways to make the RNN-T decoder (prediction network + joint network) smaller and faster without degradation in recognition performance. Our prediction network performs a simple weighted averaging of the input embeddings, and shares its embedding matrix weights with the joint networks output layer (a.k.a. weight tying, commonly used in language modeling arXiv:1611.01462 [cs.LG]). This simple design, when used in conjunction with additional Edit-based Minimum Bayes Risk (EMBR) training, reduces the RNN-T Decoder from 23M parameters to just 2M, without affecting word-error rate (WER).
Ultra-reliable low-latency communication (URLLC) requires short packets of data transmission. It is known that when the packet length becomes short, the achievable rate is subject to a penalty when compared to the channel capacity. In this paper, we
propose to use faster-than-Nyquist (FTN) signaling to compensate for the achievable rate loss of short packet communications. We investigate the performance of a combination of a low complexity detector of FTN signaling used with nonbinary low-density parity-check (NB-LDPC) codes that is suitable for low-latency and short block length requirements of URLLC systems. Our investigation shows that such combination of low-complexity FTN signaling detection and NB-LDPC codes outperforms the use of close-to-optimal FTN signaling detectors with LDPC codes in terms of error rate performance and also has a considerably lower computational complexity.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
