A Hardware Inference Accelerator for Temporal Convolutional Networks

Traditionally, Recurrent Neural Networks (RNNs) are used for time-series prediction. However, recent results have shown that Temporal Convolutional Networks (TCNs) outperform RNNs in terms of accuracy and training time. By using dilated convolutions TCNs are able to capture long term temporal dependencies from time series. The use of existing Convolutional Neural Networks (CNNs) inference accelerators for the computation of dilated convolutions significantly decreases the throughput and causes computation overhead. In order to take into account the one-dimensionality of the convolutions and presence of dilation, this paper proposes a dedicated hardware inference accelerator for TCNs. We use this accelerator to run an adaptation of WaveNet for anomaly detection in an ECG time series dataset. Our results show that it can achieve 6.3 · 10−4 DRAM access/MAC, 0.043 on-chip SRAM access/MAC and 8 ms/inference. This lower number of on-chip and off-chip memory accesses significantly decreases the overall power consumption and increases the throughput.

[1]  Houshang Darabi,et al.  LSTM Fully Convolutional Networks for Time Series Classification , 2017, IEEE Access.

[2]  Songmin Jia,et al.  Semantic Segmentation Based on Deep Convolution Neural Network , 2018 .

[3]  Hyoukjun Kwon,et al.  Rethinking NoCs for spatial neural network accelerators , 2017, 2017 Eleventh IEEE/ACM International Symposium on Networks-on-Chip (NOCS).

[4]  Hoi-Jun Yoo,et al.  DT-CNN: Dilated and Transposed Convolution Neural Network Accelerator for Real-Time Image Segmentation on Mobile Devices , 2019, 2019 IEEE International Symposium on Circuits and Systems (ISCAS).

[5]  Ninghui Sun,et al.  DianNao: a small-footprint high-throughput accelerator for ubiquitous machine-learning , 2014, ASPLOS.

[6]  Gang Xiao,et al.  SeriesNet:A Generative Time Series Forecasting Model , 2018, 2018 International Joint Conference on Neural Networks (IJCNN).

[7]  Yuan Zhang,et al.  Short-Term Residential Load Forecasting Based on LSTM Recurrent Neural Network , 2019, IEEE Transactions on Smart Grid.

[8]  Vladlen Koltun,et al.  An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling , 2018, ArXiv.

[9]  Zhiyong Luo,et al.  Combination of Convolutional and Recurrent Neural Network for Sentiment Analysis of Short Texts , 2016, COLING.

[10]  Guoqiang Peter Zhang,et al.  Neural Networks for Time-Series Forecasting , 2012, Handbook of Natural Computing.

[11]  Yunpeng Wang,et al.  Spatiotemporal Recurrent Convolutional Networks for Traffic Prediction in Transportation Networks , 2017, Sensors.

[12]  Heiga Zen,et al.  WaveNet: A Generative Model for Raw Audio , 2016, SSW.

[13]  Vivienne Sze,et al.  Efficient Processing of Deep Neural Networks: A Tutorial and Survey , 2017, Proceedings of the IEEE.

[14]  Yuanyuan Zhang,et al.  Compact Convolutional Neural Network Accelerator for IoT Endpoint SoC , 2019 .

[15]  Pranav Gokhale,et al.  Applications of Convolutional Neural Networks , 2016 .

[16]  Guokun Lai,et al.  Stochastic WaveNet: A Generative Latent Variable Model for Sequential Data , 2018, ArXiv.

[17]  William Remus,et al.  Neural Networks for Time-Series Forecasting , 2001 .

[18]  Christoforos E. Kozyrakis,et al.  Understanding sources of inefficiency in general-purpose chips , 2010, ISCA.

[19]  Les E. Atlas,et al.  Recurrent neural networks and robust time series prediction , 1994, IEEE Trans. Neural Networks.

[20]  Evangelos Spiliotis,et al.  Statistical and Machine Learning forecasting methods: Concerns and ways forward , 2018, PloS one.

[21]  Thomas Fischer,et al.  Deep learning with long short-term memory networks for financial market predictions , 2017, Eur. J. Oper. Res..

[22]  Yan Liu,et al.  Recurrent Neural Networks for Multivariate Time Series with Missing Values , 2016, Scientific Reports.

[23]  Qiao Li,et al.  AF classification from a short single lead ECG recording: The PhysioNet/computing in cardiology challenge 2017 , 2017, 2017 Computing in Cardiology (CinC).

[24]  Gábor Petneházi,et al.  Recurrent Neural Networks for Time Series Forecasting , 2018, ArXiv.

[25]  Vivienne Sze,et al.  Using Dataflow to Optimize Energy Efficiency of Deep Neural Network Accelerators , 2017, IEEE Micro.

[26]  Hoi-Jun Yoo,et al.  CNNP-v2:An Energy Efficient Memory-Centric Convolutional Neural Network Processor Architecture , 2019, 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS).

[27]  Xavier Serra,et al.  A Wavenet for Speech Denoising , 2017, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[28]  Madan Mohan Tripathi,et al.  Long term load forecasting with hourly predictions based on long-short-term-memory networks , 2018, 2018 IEEE Texas Power and Energy Conference (TPEC).

[29]  Hong Qu,et al.  Deep Dilated Convolution on Multimodality Time Series for Human Activity Recognition , 2018, 2018 International Joint Conference on Neural Networks (IJCNN).