Pith. sign in

REVIEW 7 cited by

Deep Learning in Neural Networks: An Overview

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 1404.7828 v4 pith:DEBES5B7 submitted 2014-04-30 cs.NE cs.LG

classification cs.NEcs.LG
keywords deeplearningnetworksneuralactionsartificialassignmentbackpropagation
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

In recent years, deep artificial neural networks (including recurrent ones) have won numerous contests in pattern recognition and machine learning. This historical survey compactly summarises relevant work, much of it from the previous millennium. Shallow and deep learners are distinguished by the depth of their credit assignment paths, which are chains of possibly learnable, causal links between actions and effects. I review deep supervised learning (also recapitulating the history of backpropagation), unsupervised learning, reinforcement learning & evolutionary computation, and indirect search for short programs encoding deep and large networks.

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. R-process heating implementation in hydrodynamic simulations with neural networks

    astro-ph.SR 2025-07 unverdicted novelty 7.0 of 10

    RHINE emulates r-process heating in NSM hydro simulations via neural networks trained on full nuclear trajectories, achieving <10% agreement with post-processing and boosting BH-torus ejecta mass by 40%.

  2. Efficient dataset construction using active learning and uncertainty-aware neural networks for plasma turbulent transport surrogate models

    physics.plasm-ph 2025-07 conditional novelty 6.0 of 10

    Active learning with SNGP and BNN-NCP models constructs QuaLiKiz surrogate training sets from 100 to 10,000 points, beating random sampling and approaching prior ensemble-based ADEPT efficiency.

  3. Reproducibility of machine learning analyses of 21 cm reionization maps

    astro-ph.CO 2024-12 conditional novelty 6.0 of 10

    Convolutional networks trained on 21 cm reionization images often memorize simulation boxes rather than physics, yielding high same-box test scores but poor performance on unseen simulations.

  4. Reduced Order Models and Conditional Expectation -- Analysing Parametric Low-Order Approximations

    cs.LG 2024-12 conditional novelty 4.0 of 10

    Parametric reduced-order models built by least-squares projection, including POD, reduced basis methods, and Gaussian process emulation, can be viewed as conditional expectations in a Bayesian updating framework.

  5. A Novel Privacy-Preserving Deep Learning Scheme without Using Cryptography Component

    cs.CR 2019-08 reject novelty 4.0 of 10

    A split neural network with a secret output-flip signal is claimed to protect input, output, and model privacy without cryptography, but the security argument conflates non-uniqueness with privacy and ignores known in...

  6. Attentive Deep Regression Networks for Real-Time Visual Face Tracking in Video Surveillance

    cs.CV 2019-08 conditional novelty 4.0 of 10

    An attentive GOTURN extension using VGG-Face features scores 0.807 overall on ChokePoint face tracking, compared with 0.506 for GOTURN and 0.348 for IVT.

  7. Implementing An Artificial Quantum Perceptron

    quant-ph 2024-12 reject novelty 3.0 of 10

    A Qiskit quantum perceptron can recover a hand-picked weight on a synthetic dataset, but the claimed exponential advantage is not demonstrated.

Pith tools