Training LSTM Networks With Resistive Cross-Point Devices
Open accessThe DOI matches its Crossref record; 11 of the 11 references it cites were found in a registry or an index.
Abstract
In our previous work we have shown that resistive cross point devices, so called resistive processing unit (RPU) devices, can provide significant power and speed benefits when training deep fully connected networks as well as convolutional neural networks. In this work, we further extend the RPU concept for training recurrent neural networks (RNNs) namely LSTMs. We show that the mapping of recurrent layers is very similar to the mapping of fully connected layers and therefore the RPU concept can potentially provide large acceleration factors for RNNs as well. In addition, we study the effect of various device imperfections and system parameters on training performance. Symmetry of updates becomes even more crucial for RNNs; already a few percent asymmetry results in an increase in the test error compared to the ideal case trained with floating point numbers. Furthermore, the input signal resolution to the device arrays needs to be at least 7 bits for successful training. However, we show that a stochastic rounding scheme can reduce the input signal resolution back to 5 bits. Further, we find that RPU device variations and hardware noise are enough to mitigate overfitting, so that there is less need for using dropout. Here we attempt to study the validity of the RPU approach by simulating large scale networks. For instance, the models studied here are roughly 1500 times larger than the more often studied multilayer perceptron models trained on the MNIST dataset in terms of the total number of multiplication and summation operations performed per epoch.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805 · cited 1×
“For instance, the spatial correlation in the data are tackled by convolution neural networks (CNNs) [6] [9] [10] whereas the temporal correlations can be handled by recurrent networks [11].”
BackgroundLearning representations by back-propagating errors
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986) · Nature · doi:10.1038/323533a0 · Cited by 31,892
Deep visual-semantic alignments for generating image descriptions
Karpathy, A., & Fei-Fei, L. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298932 · Cited by 4,902
In-Datacenter Performance Analysis of a Tensor Processing Unit
Jouppi, N. P., Young, C., Patil, N., Patterson, D., Agrawal, G., Bajwa, R., Bates, S., Bhatia, S., Boden, N., Borchers, A., et al. (2017) · Proceedings of the 44th Annual International Symposium on Computer Architecture · doi:10.1145/3079856.3080246 · Cited by 4,537
Training and operation of an integrated neuromorphic network based on metal-oxide memristors
Prezioso, M., Merrikh-Bayat, F., Hoskins, B. D., Adam, G. C., Likharev, K. K., & Strukov, D. B. (2015) · Nature · doi:10.1038/nature14441 · Cited by 3,001
Deep Learning with Limited Numerical Precision
Gupta, S., Agrawal, A., Gopalakrishnan, K., & Narayanan, P. (2015) · arXiv · doi:10.48550/arxiv.1502.02551 · Cited by 1,364 · cited 4×
“It is already shown that stochastic rounding helps during DNN training when used at different stages of approximate computing with reduced precision in the digital space [34].”
BackgroundInfluentialEquivalent-accuracy accelerated neural-network training using analogue memory
Ambrogio, S., Narayanan, P., Tsai, H., Shelby, R. M., Boybat, I., di Nolfo, C., Sidler, S., Giordano, M., Bodini, M., Farinha, N. C. P., et al. (2018) · Nature · doi:10.1038/s41586-018-0180-5 · Cited by 1,151
Gated Feedback Recurrent Neural Networks
Chung, J., Gulcehre, C., Cho, K., & Bengio, Y. (2015) · arXiv · doi:10.48550/arxiv.1502.02367 · Cited by 583 · cited 2×
“For instance gated recurrent units (GRUs) (Cho et al., 2014), dilated RNNs (Chang et al., 2017) or other more complex RNN architectures (Chung et al., 2015) can be mapped to RPU arrays in a similar fashion by simply changing the computations performed on the digital circuits.”
Background
Cited by
Tang, J., Yuan, F., Shen, X., Wang, Z., Rao, M., He, Y., Sun, Y., Li, X., Zhang, W., Li, Y., et al. (2019) · Advanced Materials · doi:10.1002/adma.201902761 · Cited by 834
Mixed-Precision Deep Learning Based on Computational Memory
Nandakumar, S. R., Le Gallo, M., Piveteau, C., Joshi, V., Mariani, G., Boybat, I., Karunaratne, G., Khaddam-Aljameh, R., Egger, U., Petropoulos, A., et al. (2020) · Frontiers in Neuroscience · doi:10.3389/fnins.2020.00406 · Cited by 120
John, R. A., Acharya, J., Zhu, C., Surendran, A., Bose, S. K., Chaturvedi, A., Tiwari, N., Gao, Y., He, Y., Zhang, K. K., et al. (2020) · Nature Communications · doi:10.1038/s41467-020-16985-0 · Cited by 68
Tsai, H., Ambrogio, S., Mackin, C., Narayanan, P., Shelby, R. M., Rocki, K., Chen, A., & Burr, G. W. (2019) · 2019 Symposium on VLSI Technology · doi:10.23919/vlsit.2019.8776519 · Cited by 47
Rasch, M. J., Gokmen, T., Rigotti, M., & Haensch, W. (2019) · Frontiers in Neuroscience · doi:10.3389/fnins.2019.00753 · Cited by 14
Self-citation
Metadata
- Authors
- Gokmen, T., Rasch, M. J., & Haensch, W.
- Venue
- Frontiers in Neuroscience
- Publisher
- Frontiers Media SA
- Published
- 2018-10-24
- Volume
- 12
- Pages
- 745-745
- ISSN
- 1662-453X (ISSN-L)
- OpenAlex
- W2805354944
- Cited by
- 53
- References
- 11
- FWCI
- 3.48
- Type
- journal article
- Language
- en
- Open access
- gold
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Training LSTM Networks With Resistive Cross-Point Devices. https://app.cochat.ai/papers/10.3389/fnins.2018.00745
- The paper
- Gokmen, T., Rasch, M. J., & Haensch, W. (2018). Training LSTM Networks With Resistive Cross-Point Devices. Frontiers in Neuroscience. https://doi.org/10.3389/fnins.2018.00745
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.