Pith. sign in

REVIEW 7 cited by

Sparse arrays of signatures for online character recognition

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1308.0371 v2 pith:XLBP2UO5 submitted 2013-08-01 cs.CV cs.NE

classification cs.CVcs.NE
keywords characterchineseonlinesparsecasia-olhwdb1characterscollectionconsumption
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

In mathematics the signature of a path is a collection of iterated integrals, commonly used for solving differential equations. We show that the path signature, used as a set of features for consumption by a convolutional neural network (CNN), improves the accuracy of online character recognition---that is the task of reading characters represented as a collection of paths. Using datasets of letters, numbers, Assamese and Chinese characters, we show that the first, second, and even the third iterated integrals contain useful information for consumption by a CNN. On the CASIA-OLHWDB1.1 3755 Chinese character dataset, our approach gave a test error of 3.58%, compared with 5.61% for a traditional CNN [Ciresan et al.]. A CNN trained on the CASIA-OLHWDB1.0-1.2 datasets won the ICDAR2013 Online Isolated Chinese Character recognition competition. Computationally, we have developed a sparse CNN implementation that make it practical to train CNNs with many layers of max-pooling. Extending the MNIST dataset by translations, our sparse CNN gets a test error of 0.31%.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Advances in Neural Controlled Differential Equations

    cs.LG 2026-07 conditional novelty 7.0 of 10

    Linear NCDEs replace non-linear vector fields with linear ones, enabling parallel-in-time training via associative scans while retaining maximal theoretical expressivity and achieving state-of-the-art time series perf...

  2. Learning with Expected Signatures: Theory and Applications

    stat.ML 2025-05 conditional novelty 7.0 of 10

    The paper proves consistency and asymptotic normality for empirical expected signature estimators under irregular and dependent sampling and proposes a martingale correction that lowers estimator variance.

  3. Global universal approximation with Brownian signatures

    math.PR 2025-12 conditional novelty 6.0 of 10

    Linear functionals on the signature of the time-extended Brownian motion are dense in L^p of the Wiener measure, and therefore approximate any p-integrable adapted process and any Itô SDE solution.

  4. Learning stochastic differential equations using RNN with log signature features

    cs.LG 2019-08 conditional novelty 6.0 of 10

    A hybrid network that feeds coarse log-signature features into an RNN is universal for SDE solution maps and beats baseline RNNs on action and gesture recognition benchmarks.

  5. Deep Learning for Estimating Synaptic Health of Primary Neuronal Cell Culture

    eess.IV 2019-08 conditional novelty 5.0 of 10

    A fine-tuned ResNet18 classifies images of Aβ-treated versus untreated neurons with 99.6% accuracy and screens 36 compounds, none of which showed a protective effect.

  6. Scalable Machine Learning Algorithms using Path Signatures

    stat.ML 2025-06 conditional novelty 4.0 of 10

    Path signatures can be embedded in Gaussian process, deep learning, kernel, and graph diffusion models to match or beat established baselines on time series and graph benchmarks.

  7. Path Signatures for Feature Extraction. An Introduction to the Mathematics Underpinning an Efficient Machine Learning Technique

    cs.LG 2025-06 unverdicted

    A tutorial explaining how path signatures, built from iterated integrals, can serve as features for classifying time series.

Pith tools