On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,742 papers · 148 categories

Trend · papers per month

count % of corpus

5 results for “RPN 2”

RPN: Reconciled Polynomial Network Towards Unifying PGMs, Kernel SVMs, MLP and KANcs.LG

RPN unifies various models with a reconciled polynomial network.

problem Unifying diverse models for deep function learning.

method RPN disentangles functions into inner products of expansion and reconciliation functions.

result RPN accurately approximates underlying functions for data distributions.

deep learning model unification polynomial network reconciliation function approximation

2024-07-05abs ↗pdf ↗

RPN 2: On Interdependence Function Learning Towards Unifying and Advancing CNN, RNN, GNN, and Transformercs.LG

RPN 2 improves function learning by modeling data interdependence.

problem Invalid assumption of input data independence leads to performance degradation.

method Integrates data and structural interdependence functions into RPN 2's architecture.

result Significantly improves learning performance and expands unifying potential.

data interdependence function learning RPN 2 CNN RNN

2024-11-17abs ↗pdf ↗

RPN: A Residual Pooling Network for Efficient Federated Learningcs.LG

RPN reduces communication costs in federated learning.

problem Efficient communication in federated learning with complex models.

method Residual Pooling Network (RPN) for compression.

result RPN achieves similar performance with reduced data transmission.

federated learning compression residual pooling end-to-end CNN

2020-01-23abs ↗pdf ↗

A Bayesian Perspective of Convolutional Neural Networks through a Deconvolutional Generative Modelcs.CV

Inspired by the success of Convolutional Neural Networks (CNNs) for supervised prediction in images, we design the Deconvolutional Generative Model (DGM), a new probabilistic generative model whose inference calculations correspond to those in a given CNN architecture. The DGM uses a CNN to design the prior distributio…

2018-11-01abs ↗pdf ↗

Through-Wall Pose Imaging in Real-Time with a Many-to-Many Encoder/Decoder Paradigmcs.CV

Overcoming the visual barrier and developing "see-through vision" has been one of mankind's long-standing dreams. Unlike visible light, Radio Frequency (RF) signals penetrate opaque obstructions and reflect highly off humans. This paper establishes a deep-learning model that can be trained to reconstruct continuous vid…

2019-03-15abs ↗pdf ↗