pith. sign in

arxiv: 1804.09028 · v1 · pith:SGTXQZ3Gnew · submitted 2018-04-24 · 💻 cs.LG · cs.CL· stat.ML

Estimate and Replace: A Novel Approach to Integrating Deep Neural Networks with Existing Applications

classification 💻 cs.LG cs.CLstat.ML
keywords applicationexistingdeepapplicationsapproachestimateestimatornetwork
0
0 comments X
read the original abstract

Existing applications include a huge amount of knowledge that is out of reach for deep neural networks. This paper presents a novel approach for integrating calls to existing applications into deep learning architectures. Using this approach, we estimate each application's functionality with an estimator, which is implemented as a deep neural network (DNN). The estimator is then embedded into a base network that we direct into complying with the application's interface during an end-to-end optimization process. At inference time, we replace each estimator with its existing application counterpart and let the base network solve the task by interacting with the existing application. Using this 'Estimate and Replace' method, we were able to train a DNN end-to-end with less data and outperformed a matching DNN that did not interact with the external application.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 11 Pith papers

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

  1. Silicate cosmic dust grain collisions in the interstellar medium: A molecular dynamics study

    astro-ph.GA 2026-05 unverdicted novelty 7.0

    MD simulations of 5-50 Å silicate grains find shattering thresholds of ~6 km/s for both SiO2 and astrodust compositions, twice the canonical 2.7 km/s value, with shattered size distributions inconsistent with prior po...

  2. Muon is Not That Special: Random or Inverted Spectra Work Just as Well

    cs.LG 2026-05 unverdicted novelty 7.0

    Muon succeeds by guaranteeing local step-size optimality rather than by tracking any ideal global geometry, as random-spectrum and quasi-norm variants match its performance on language models.

  3. When Support Escalates Distress: Regulation and Escalation in LLM Responses to Venting and Advice-Seeking

    cs.HC 2026-05 unverdicted novelty 6.0

    LLM responses mirror venting with higher regulation and escalation; therapist personas lower escalation while preserving regulation, and lay raters miss escalation.

  4. Stationary subspace analysis for spatial data

    stat.ME 2026-05 unverdicted novelty 6.0

    Introduces spSSA extending SSA to spatial data via three generalized eigenvalue procedures and a data augmentation method to estimate nonstationary subspace dimension.

  5. Symplectic Neural Operators for Learning Infinite Dimensional Hamiltonian Systems

    math.DS 2026-05 unverdicted novelty 6.0

    Symplectic Neural Operators preserve symplectic structure for learning infinite-dimensional Hamiltonian PDEs and deliver improved long-term energy stability in theory and experiments.

  6. Letting the neural code speak: Automated characterization of monkey visual neurons through human language

    q-bio.NC 2026-05 unverdicted novelty 6.0

    Natural language descriptions generated via a closed-loop pipeline with digital twins capture the selectivity of most neurons in macaque V1 and V4, with synthesized images driving 96% of V4 neurons into the top or bot...

  7. Letting the neural code speak: Automated characterization of monkey visual neurons through human language

    q-bio.NC 2026-05 unverdicted novelty 6.0

    Natural-language descriptions generated and verified through generative models and digital twins capture the selectivity of most neurons in macaque V1 and V4.

  8. Liberata -- Graph Scientometrics for a Share Based System of Academic Publishing

    cs.DL 2026-05 unverdicted novelty 5.0

    Liberata introduces a graph-based system using continuous contribution shares and weighted citations to derive metrics for impact, risk, collaboration, and quality control in academic publishing.

  9. Detecting Language Model Attacks with Perplexity

    cs.CL 2023-08 unverdicted novelty 5.0

    Jailbreak prompts with adversarial suffixes have high GPT-2 perplexity, and a LightGBM model on perplexity and length detects most attacks.

  10. A critical comparison of handling zeros in high-dimensional compositional count data

    stat.OT 2026-05 unverdicted novelty 4.0

    A review consolidating zero-handling methods for compositional count data, critiquing log-ratio assumptions, and comparing imputation strategies adapted to discrete zero-inflated counts.

  11. Student Classroom Behavior Recognition Based on Improved YOLOv8s

    cs.CV 2026-04 unverdicted novelty 3.0

    An updated YOLOv8s detector improves student behavior recognition in crowded classrooms by 1.8-2.1% mAP through added feature modules and a reweighted loss.