Browse State-of-the-Art › Handwritten Digit Recognition

Handwritten Digit Recognition

29 papers with code · 2 benchmarks · 7 datasets archive 2025-07-28

Computer VisionMethodologyNatural Language Processing

Benchmarks archive 2025-07-28

2 leaderboard tables shown for this task, 2 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology 3 newer papers were judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): MNIST (3 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
MNIST (2 rows) CNN Effective Handwritten Digit Recognition using Deep Convolution... code — Compare
Digits (1 row) LeNet-5 Gradient-based learning applied to document recognition code — Compare

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

7 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Parent tasks archive 2025-07-28

Papers archive 2025-07-28

archive papers tagged: 107 · with a code link: 29 · where Syntology ran a sample: 1 (1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (1 of 107 tagged: 1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)

Page 1 of 2: papers 1 to 100 of 107, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.

Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.

  • 20 Feb 2019 5 repositories listed
    In this paper, we propose a novel method to compute the learning rate for training deep neural networks with stochastic gradient descent.
  • 22 Apr 2024 2 repositories listed
    Attribution methods are primarily designed to study the distribution of input component contributions to individual model predictions.
  • 8 Apr 2020 2 repositories listed
    In this letter, we contribute a multi-language handwritten digit recognition dataset named MNIST-MIX, which is the largest dataset of the same type in terms of both languages and data samples.
  • We discuss the trade-off between model accuracy and resource consumption.
  • 17 Oct 2015 2 repositories listed
    Gradient backpropagation (BP) requires symmetric feedforward and feedback connections -- the same weights must be used for forward and backward passes.
  • 10 May 2025 1 repository listed
    The LST based on the idea of sharing the weights of one fullyconnected (FC) layer to process all rows of an image.
  • 18 Mar 2024 1 repository listed
    In this work, we present a robust and cost-effective approach that handles multilingual handwritten numeral recognition across a wide range of languages.
  • 14 Mar 2024 1 repository listed
    The proposed model returns a set of prototype subspaces and a relevance vector.
  • 5 Sep 2023 1 repository listed
    We show that by using polynomial building blocks, we can achieve the same accuracy using considerably fewer layers of soft logic than by using linear functions, leading to significant latency and area improvements.
  • 14 Mar 2023 1 repository listed
    Air-writing refers to virtually writing linguistic characters through hand gestures in three-dimensional space with six degrees of freedom.
  • 1 Feb 2023 1 repository listed
    Herein, we present Stratus, an end-to-end full-stack deep learning application deployed on the cloud.
  • 30 May 2022 1 repository listed
    Recognizing handwritten digits is one of the most active research areas in computer vision, as there are a variety of applications, such as automatic identification of digits in bank checks and vehicle numbers.
  • 11 Jun 2021 1 repository listed
    Based on this, we propose a general-purpose deep clustering framework which radically integrates representation learning and clustering into a single pipeline for the first time.
  • 14 Mar 2021 1 repository listed
    Handwritten digit or numeral recognition is one of the classical issues in the area of pattern recognition and has seen tremendous advancement because of the recent wide availability of computing resources.
  • 1 Mar 2021 1 repository listed
    This article presents the first results from using a learning classifier system capable of performing adaptive computation with deep neural networks.
  • 18 Dec 2020 1 repository listed
    Previous work has shown that it is possible to train neuronal cultures on Multi-Electrode Arrays (MEAs), to recognize very simple patterns.
  • 15 Dec 2020 1 repository listed
    Classification of quantum data is essential for quantum machine learning and near-term quantum technologies.
  • 26 Jun 2020 1 repository listed
    To improve the performance of the Bangla handwritten digit recognition system, we have designed a model, in which all basic Bangla digits have been classified.
  • 30 Apr 2020 1 repository listed
    This paper proposed a simple neural network approach towards handwritten digit recognition using convolution.
  • 20 Dec 2019 1 repository listed
    Executing deep neural networks for inference on the server-class or cloud backend based on data generated at the edge of Internet of Things is desirable due primarily to the limited compute power of edge devices and the…
  • 10 Jun 2019 1 repository listed
    BDNet is a densely connected deep convolutional neural network model used to classify (recognize) Bengali handwritten numeral digits.
  • 28 Feb 2018 1 repository listed
    We propose an interpretable deep structure namely Frank-Wolfe Network (F-W Net), whose architecture is inspired by unrolling and truncating the Frank-Wolfe algorithm for solving an Lₚ-norm constrained problem with p≥1.
  • 22 Feb 2018 1 repository listed
    This paper is under consideration for acceptance in
  • 3 May 2017 1 repository listed
    We present a specialized verification algorithm that employs this approximation in a search process in which it infers additional node phases for the non-linear nodes in the network from partial node phase assignments…
  • 2 Jul 2016 1 repository listed
    In this paper, we consider the joint task of simultaneously optimizing (i) the weights of a deep neural network, (ii) the number of neurons for each hidden layer, and (iii) the subset of active input features (i. e.…
  • 9 Oct 2015 1 repository listed
    Faced with continuously increasing scale of data, original back-propagation neural network based machine learning algorithm presents two non-trivial challenges: huge amount of data makes it difficult to maintain both…
  • 21 Jul 2015 1 repository listed
    The architecture is not limited to handwriting recognition, but is generally applicable as an extremely fast pattern recognition processor for various kinds of patterns such as speech and images.
  • 1 Mar 2010 1 repository listed
    Good old on-line back-propagation for plain multi-layer perceptrons yields a very low 0.
  • 1 Nov 1998 1 repository listed
    It uses convolutional neural network character recognizers combined with global training techniques to provide record accuracy on business and personal cheques.
  • Devanagari Digit Recognition using Quantum Machine Learning
    8 Jun 2025 0 repositories listed
    Handwritten digit recognition in regional scripts, such as Devanagari, is crucial for multilingual document digitization, educational tools, and the preservation of cultural heritage.
  • An Adaptive Clustering Scheme for Client Selections in Communication-Efficient Federated Learning
    11 Apr 2025 0 repositories listed
  • Handwritten Digit Recognition: An Ensemble-Based Approach for Superior Performance
    8 Mar 2025 0 repositories listed
  • Handling Missing Data in Downstream Tasks With Distribution-Preserving Guarantees
    23 Jan 2025 0 repositories listed
  • Machine Unlearning using Forgetting Neural Networks
    29 Oct 2024 0 repositories listed
  • Approaching Metaheuristic Deep Learning Combos for Automated Data Mining
    16 Oct 2024 0 repositories listed
  • Fractional signature: a generalisation of the signature inspired by fractional calculus
    24 Jul 2024 0 repositories listed
  • Verification for Object Detection -- IBP IoU
    30 Jan 2024 0 repositories listed
  • Digital-analog hybrid matrix multiplication processor for optical neural networks
    26 Jan 2024 0 repositories listed
  • Polariton lattices as binarized neuromorphic networks
    14 Jan 2024 0 repositories listed
  • NeuroWrite: Predictive Handwritten Digit Classification using Deep Neural Networks
    2 Nov 2023 0 repositories listed
  • Neuromorphic Hebbian learning with magnetic tunnel junction synapses
    21 Aug 2023 0 repositories listed
  • Analyzing the vulnerabilities in SplitFed Learning: Assessing the robustness against Data Poisoning Attacks
    4 Jul 2023 0 repositories listed
  • Quantum Neural Network for Quantum Neural Computing
    15 May 2023 0 repositories listed
  • Image Moment Invariants to Rotational Motion Blur
    25 Mar 2023 0 repositories listed
  • Composite Optimization Algorithms for Sigmoid Networks
    1 Mar 2023 0 repositories listed
  • Bengali Handwritten Digit Recognition using CNN with Explainable AI
    23 Dec 2022 0 repositories listed
  • Efficient approach of using CNN based pretrained model in Bangla handwritten digit recognition
    19 Sep 2022 0 repositories listed
  • Two Decades of Bengali Handwritten Digit Recognition: A Survey
    5 Jun 2022 0 repositories listed
  • A Classical Approach to Handcrafted Feature Extraction Techniques for Bangla Handwritten Digit Recognition
    25 Jan 2022 0 repositories listed
  • Experimental Demonstration of Neuromorphic Network with STT MTJ Synapses
    9 Dec 2021 0 repositories listed
  • Handwritten Digit Recognition Using Improved Bounding Box Recognition Technique
    10 Nov 2021 0 repositories listed
  • Efficient Majority Voting in Digital Hardware
    9 Aug 2021 0 repositories listed
  • Efficient Learning of Pinball TWSVM using Privileged Information and its applications
    14 Jul 2021 0 repositories listed
  • Model of the Weak Reset Process in HfOx Resistive Memory for Deep Learning Frameworks
    2 Jul 2021 0 repositories listed
  • Handwritten Digit Recognition using Machine and Deep Learning Algorithms
    23 Jun 2021 0 repositories listed
  • Multi-script Handwritten Digit Recognition Using Multi-task Learning
    15 Jun 2021 0 repositories listed
  • Photonic single perceptron at Giga-OP/s speeds with Kerr microcombs for scalable optical neural networks
    12 May 2021 0 repositories listed
  • Alleviation of Temperature Variation Induced Accuracy Degradation in Ferroelectric FinFET Based Neural Network
    3 Mar 2021 0 repositories listed
  • Discriminative Multiple Canonical Correlation Analysis for Information Fusion
    28 Feb 2021 0 repositories listed
  • The Labeled Multiple Canonical Correlation Analysis for Information Fusion
    28 Feb 2021 0 repositories listed
  • Gradient-adjusted Incremental Target Propagation Provides Effective Credit Assignment in Deep Neural Networks
    23 Feb 2021 0 repositories listed
  • Convolutional Neural Network with Pruning Method for Handwritten Digit Recognition
    15 Jan 2021 0 repositories listed
  • Evaluation of Deep Learning Models for Kannada Handwritten Digit Recognition
    9 Dec 2020 0 repositories listed
  • Image Pre-processing on NumtaDB for Bengali Handwritten Digit Recognition
    18 Aug 2020 0 repositories listed
  • Contraction Mapping of Feature Norms for Classifier Learning on the Data with Different Quality
    27 Jul 2020 0 repositories listed
  • Reinforcement Learning Based Handwritten Digit Recognition with Two-State Q-Learning
    28 Jun 2020 0 repositories listed
  • The Golden Ratio of Learning and Momentum
    8 Jun 2020 0 repositories listed
  • Neural Network for Low-Memory IoT Devices and MNIST Image Recognition Using Kernels Based on Logistic Map
    4 Jun 2020 0 repositories listed
  • Atom Search Optimization with Simulated Annealing -- a Hybrid Metaheuristic Approach for Feature Selection
    10 May 2020 0 repositories listed
  • Robust Tensor Decomposition for Image Representation Based on Generalized Correntropy
    10 May 2020 0 repositories listed
  • Ghost Handwritten Digit Recognition based on Deep Learning
    5 Apr 2020 0 repositories listed
  • Capsule-Based Persian/Arabic Robust Handwritten Digit Recognition Using EM Routing
    8 Dec 2019 0 repositories listed
  • Meta-neural-network for Realtime and Passive Deep-learning-based Object Recognition
    16 Sep 2019 0 repositories listed
  • Recognition of Handwritten Digit using Convolutional Neural Network in Python with Tensorflow and Comparison of Performance for Various Hidden Layers
    12 Sep 2019 0 repositories listed
  • Inference with Hybrid Bio-hardware Neural Networks
    28 May 2019 0 repositories listed
  • Clustering Images by Unmasking - A New Baseline
    2 May 2019 0 repositories listed
  • How Machine (Deep) Learning Helps Us Understand Human Learning: the Value of Big Ideas
    16 Feb 2019 0 repositories listed
  • Deep Neural Network Approximation Theory
    8 Jan 2019 0 repositories listed
  • Fuzzy Controller of Reward of Reinforcement Learning For Handwritten Digit Recognition
    17 Dec 2018 0 repositories listed
  • A multi-class structured dictionary learning method using discriminant atom selection
    4 Dec 2018 0 repositories listed
  • Assessing four Neural Networks on Handwritten Digit Recognition Dataset (MNIST)
    16 Nov 2018 0 repositories listed
  • Handwritten Digit Recognition by Elastic Matching
    24 Jul 2018 0 repositories listed
  • Markov chain Hebbian learning algorithm with ternary synaptic units
    23 Nov 2017 0 repositories listed
  • Few-Shot Adversarial Domain Adaptation
    5 Nov 2017 0 repositories listed
  • A Supervised STDP-based Training Algorithm for Living Neural Networks
    30 Oct 2017 0 repositories listed
  • Towards a Unified Compositional Model for Visual Pattern Modeling
    1 Oct 2017 0 repositories listed
  • Towards Poisoning of Deep Learning Algorithms with Back-gradient Optimization
    29 Aug 2017 0 repositories listed
  • Nonnegative Restricted Boltzmann Machines for Parts-based Representations Discovery and Predictive Model Stabilization
    18 Aug 2017 0 repositories listed
  • Neuron Pruning for Compressing Deep Networks using Maxout Architectures
    21 Jul 2017 0 repositories listed
  • Developing All-Skyrmion Spiking Neural Network
    8 May 2017 0 repositories listed
  • Handwritten Arabic Numeral Recognition using Deep Learning Neural Networks
    15 Feb 2017 0 repositories listed
  • Randomized Prediction Games for Adversarial Machine Learning
    3 Sep 2016 0 repositories listed
  • Recurrent neural network training with preconditioned stochastic gradient descent
    14 Jun 2016 0 repositories listed
  • FPGA Based Implementation of Deep Neural Networks Using On-chip Memory Only
    4 Feb 2016 0 repositories listed
  • Matrix Variate RBM and Its Applications
    5 Jan 2016 0 repositories listed
  • Bayesian mixtures of spatial spline regressions
    4 Aug 2015 0 repositories listed
  • Massively Deep Artificial Neural Networks for Handwritten Digit Recognition
    17 Jul 2015 0 repositories listed
  • Natural Scene Recognition Based on Superpixels and Deep Boltzmann Machines
    24 Jun 2015 0 repositories listed
  • Iterated Support Vector Machines for Distance Metric Learning
    2 Feb 2015 0 repositories listed
  • A GA Based approach for selection of local features for recognition of handwritten Bangla numerals
    22 Jan 2015 0 repositories listed

Syntology lines on 1 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections