A Variation-Tolerant In-Memory Machine Learning Classifier via On-Chip Training
The DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.
Abstract
This paper presents a robust deep in-memory machine learning classifier with a stochastic gradient descent (SGD)-based on-chip trainer using a standard 16-kB 6T SRAM array. The deep in-memory architecture (DIMA) enhances both energy efficiency and throughput over conventional digital architectures by reading multiple bits per bit line (BL) per read cycle and by employing mixed-signal processing in the periphery of the bit-cell array. Though these techniques improve the energy efficiency and latency, DIMA's analog nature makes it sensitive to process, voltage, and temperature (PVT) variations, especially under reduced BL swings. On-chip training enables DIMA to adapt to chip-specific variations in PVT as well as data statistics, thereby further enhancing its energy efficiency. The 65-nm CMOS prototype IC demonstrates this improvement by realizing an on-chip trainable support vector machine. By learning chipspecific weights, on-chip training enables robust operation under reduced BL swing leading to a 2.4 times reduction in energy over an off-chip trained DIMA. The prototype IC in 65-nm CMOS consumes 42 pJ/decision at 32 M decisions/s, corresponding to 3.12 TOPS/W (1 OP = one 8-b × 8-b MAC) during inference, thereby achieving a reduction of 21 times in energy and 100 times in energy-delay product as compared with a conventional digital architecture. The energy overhead of training is <;26% per decision for SGD batch sizes of 128 and higher.
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
Cortes, C., & Vapnik, V. (1995) · Machine Learning · doi:10.1007/bf00994018 · Cited by 59,421
Eyeriss: An Energy-Efficient Reconfigurable Accelerator for Deep Convolutional Neural Networks
Chen, Y.-H., Krishna, T., Emer, J. S., & Sze, V. (2017) · IEEE Journal of Solid-State Circuits · doi:10.1109/jssc.2016.2616357 · Cited by 3,247
Hubara, I., Soudry, D., & Yaniv, R. E. (2016) · arXiv · doi:10.48550/arxiv.1602.02505 · Cited by 1,667
Biswas, A., & Chandrakasan, A. P. (2018) · 2018 IEEE International Solid - State Circuits Conference - (ISSCC) · doi:10.1109/isscc.2018.8310397 · Cited by 337
Khwa, W.-S., Chen, J.-J., Li, J.-F., Si, X., Yang, E.-Y., Sun, X., Liu, R., Chen, P.-Y., Li, Q., Yu, S., et al. (2018) · 2018 IEEE International Solid - State Circuits Conference - (ISSCC) · doi:10.1109/isscc.2018.8310401 · Cited by 260 · cited 2×
“[10] [11] [13] [15] This Work Technology 130nm 65nm 65nm 65nm 65nm Algorithm AdaBoost SVM CNN DNN SVM Dataset MNIST MIT-CBCL MNIST MNIST MIT-CBCL On-chip memory (kB) 2 16 2 0.”
Method
Research works printed but not linked: 21
- 10.1109/JSSC.2016.2642198 · DOI · Paper page
- 10.1109/JSSC.2017.2782087 · DOI · Paper page
- 10.1109/JSSC.2018.2822703 · DOI
- chen, 2018, A 65 nm 1 Mb nonvolatile computing-in-memory ReRAM macro with sub-16 ns multiply-and-accumulate for binary DNN AI edge processors, IEEE Int Solid-State Circuits Conf (ISSCC) Dig Tech Papers, 494
- 10.1109/ISSCC.2018.8310399 · DOI · Paper page
- sakr, 2017, Analytical guarantees on numerical precision of deep neural networks, Proc Int Conf Mach Learn, 3007
- 10.1109/ACSSC.2017.8335699 · DOI
- 10.1109/ISSCC.2017.7870350 · DOI · Paper page
- 10.1109/MICRO.2003.1253179 · DOI · Paper page
- moons, 2017, Envision: A 0.26-to-10 TOPS/W subword-parallel dynamic-voltage-accuracy-frequency-scalable convolutional neural network processor in 28 nm FDSOI, IEEE Int Solid-State Circuits Conf (ISSCC) Dig Tech Papers, 246
- 10.1109/ISSCC.2018.8310262 · DOI · Paper page
- whatmough, 2017, A 28 nm SOC with a 1.2 GHz 568 nJ/prediction sparse deep-neural-network engine with >0.1 timing error rate tolerance for IOT applications, IEEE Int Solid-State Circuits Conf (ISSCC) Dig Tech Papers, 242
- 10.1109/ICASSP.2014.6855225 · DOI · Paper page
- chen, 2014, DianNao: A small-footprint high-throughput accelerator for ubiquitous machine-learning, ACM SIGPLAN Notices, 49, 269, 10.1145/2644865.2541967 · DOI · Paper page
- horowitz, 2014, Computing’s energy problem (and what we can do about it), IEEE Int Solid-State Circuits Conf (ISSCC) Dig Tech Papers, 10
- 10.1109/ICASSP.2015.7178127 · DOI
- bottou, 2016, Optimization Methods for Large-Scale Machine Learning
- 10.1109/ESSCIRC.2017.8094576 · DOI
- gonugondla, 2018, A 42 pJ/decision 3.12 TOPS/W robust in-memory machine learning classifier with on-chip training, IEEE Int Solid-State Circuits Conf (ISSCC) Dig Tech Papers, 490
- 2000, Center for Biological and Computational Learning at MIT
- 10.1109/ICASSP.2017.7952334 · DOI
Cited by
Memory devices and applications for in-memory computing
Sebastian, A., Le Gallo, M., Khaddam-Aljameh, R., & Eleftheriou, E. (2020) · Nature Nanotechnology · doi:10.1038/s41565-020-0655-z · Cited by 2,289
Towards spike-based machine intelligence with neuromorphic computing
Roy, K., Jaiswal, A., & Panda, P. (2019) · Nature · doi:10.1038/s41586-019-1677-2 · Cited by 2,190
Accurate deep neural network inference using computational phase-change memory
Joshi, V., Le Gallo, M., Haefeli, S., Boybat, I., Nandakumar, S. R., Piveteau, C., Dazzi, M., Rajendran, B., Sebastian, A., & Eleftheriou, E. (2020) · Nature Communications · doi:10.1038/s41467-020-16108-9 · Cited by 490
Accurate deep neural network inference using computational phase-change memory
Joshi, V., Gallo, M. L., Haefeli, S., Boybat, I., Nandakumar, S. R., Piveteau, C., Dazzi, M., Rajendran, B., Sebastian, A., & Eleftheriou, E. S. (2020) · RePEc: Research Papers in Economics · doi:10.3929/ethz-b-000416797 · Cited by 379
C3SRAM: An In-Memory-Computing SRAM Macro Based on Robust Capacitive Coupling Computing Mechanism
Jiang, Z., Yin, S., Seo, J.-S., & Seok, M. (2020) · IEEE Journal of Solid-State Circuits · doi:10.1109/jssc.2020.2992886 · Cited by 324
Metadata
- Authors
- Gonugondla, S. K., Kang, M., & Shanbhag, N. R.
- Venue
- IEEE Journal of Solid-State Circuits
- Published
- 2018-11
- Volume
- 53
- Issue
- 11
- Pages
- 3163-3173
- ISSN
- 0018-9200 (ISSN-L)
- 1558-173X
- OpenAlex
- W2891442728
- Cited by
- 123
- References
- 5
- FWCI
- 5.74
- Type
- journal article
- Language
- en
- Open access
- closed
- Funders
- Systems On Nanoscale Information fabriCs (SONIC), one of the six SRC STARnet Centers, sponsored by MARCO and DARPA
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
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.