paper-with-me

홈 › Papers

TENNs-PLEIADES: Building Temporal Kernels with Orthogonal Polynomials

2024-05-20 · Yan Ru Pei, Olivier Coenen

We introduce a neural network named PLEIADES (PoLynomial Expansion In Adaptive Distributed Event-based Systems), belonging to the TENNs (Temporal Neural Networks) architecture. We focus on interfacing these networks with event-based data to perform online spatiotemporal classification and detection with low latency. By virtue of using structured temporal kernels and event-based data, we have the freedom to vary the sample rate of the data along with the discretization step-size of the network without additional finetuning. We experimented with three event-based benchmarks and obtained state-of-the-art results on all three by large margins with significantly smaller memory and compute costs. We achieved: 1) 99.59% accuracy with 192K parameters on the DVS128 hand gesture recognition dataset and 100% with a small additional output filter; 2) 99.58% test accuracy with 277K parameters on the AIS 2024 eye tracking challenge; and 3) 0.556 mAP with 576k parameters on the PROPHESEE 1 Megapixel Automotive Detection Dataset.

📄 PDF Abstract BibTeX arXiv:2405.12179

Code (1)

peabrane/pleiades 공식 구현 pytorch

Tasks

Gesture RecognitionHand Gesture RecognitionHand-Gesture Recognition

Methods 이 논문이 사용한 방법론

Focus 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Deep Neural Networks for automatic extraction of features in time series satellite images

2020-08-17 · Gael Kamdem De Teyou, Yuliya Tarabalka, Isabelle Manighetti, Rafael Almar 외

Many earth observation programs such as Landsat, Sentinel, SPOT, and Pleiades produce huge volume of medium to high resolution multi-spectral images every day that can be organized in time series. In this work, we exploi…

Earth ObservationLand Cover ClassificationTime SeriesTime Series Analysis

Convolutional unitary or orthogonal recurrent neural networks

2023-02-14 · Marcelo O. Magnasco

Recurrent neural networks are extremely powerful yet hard to train. One of their issues is the vanishing gradient problem, whereby propagation of training signals may be exponentially attenuated, freezing training. Use o…

Beyond the Gegenbauer Paradigm: q-Orthogonal Kernels for Machine Learning

2026-08-04 · Álvaro Sánchez-Paniagua Ríos, Juan P. Llerena, Alberto Lastra, Nuria Torrado 외 arxiv

The performance of Support Vector Machines (SVMs) critically depends on the kernel function choice, which enables implicit mapping of data into high-dimensional feature spaces. While classical kernels like Radial Basis F…

Vehicle detection and counting from VHR satellite images: efforts and open issues

2019-10-22 · Alice Froidevaux, Andréa Julier, Agustin Lifschitz, Minh-Tan Pham 외

Detection of new infrastructures (commercial, logistics, industrial or residential) from satellite images constitutes a proven method to investigate and follow economic and urban growth. The level of activities or exploi…

Segmentationvehicle detection

Structural interpretability in SVMs with truncated orthogonal polynomial kernels

2026-04-16 · Víctor Soto-Larrosa, Nuria Torrado, Edmundo J. Huertas arxiv

We study post-training interpretability for Support Vector Machines (SVMs) built from truncated orthogonal polynomial kernels. Since the associated reproducing kernel Hilbert space is finite-dimensional and admits an exp…