paper-with-me

홈 › Papers

QuadraLib: A Performant Quadratic Neural Network Library for Architecture Optimization and Design Exploration

2022-04-01 · Zirui Xu, Fuxun Yu, JinJun Xiong, Xiang Chen

The significant success of Deep Neural Networks (DNNs) is highly promoted by the multiple sophisticated DNN libraries. On the contrary, although some work have proved that Quadratic Deep Neuron Networks (QDNNs) show better non-linearity and learning capability than the first-order DNNs, their neuron design suffers certain drawbacks from theoretical performance to practical deployment. In this paper, we first proposed a new QDNN neuron architecture design, and further developed QuadraLib, a QDNN library to provide architecture optimization and design exploration for QDNNs. Extensive experiments show that our design has good performance regarding prediction accuracy and computation consumption on multiple learning tasks.

📄 PDF Abstract BibTeX arXiv:2204.01701

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

TorchFL: A Performant Library for Bootstrapping Federated Learning Experiments

2022-11-01 · Vivek Khimani, Shahin Jabbari

With the increased legislation around data privacy, federated learning (FL) has emerged as a promising technique that allows the clients (end-user) to collaboratively train deep learning (DL) models without transferring …

Federated Learning

frax: Fast Robot Kinematics and Dynamics in JAX

2026-04-05 · Daniel Morton, Marco Pavone arxiv

In robot control, planning, and learning, there is a need for rigid-body dynamics libraries that are highly performant, easy to use, and compatible with CPUs and accelerators. While existing libraries often excel at eith…

Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks

2019-09-03 · Minjie Wang, Da Zheng, Zihao Ye, Quan Gan 외

Advancing research in the emerging field of deep graph learning requires new tools to support tensor computation over graphs. In this paper, we present the design principles and implementation of Deep Graph Library (DGL)…

Graph LearningNode Classification

Flexible Differentiable Optimization via Model Transformations

2022-06-10 · Mathieu Besançon, Joaquim Dias Garcia, Benoît Legat, Akshay Sharma

We introduce DiffOpt.jl, a Julia library to differentiate through the solution of optimization problems with respect to arbitrary parameters present in the objective and/or constraints. The library builds upon MathOptInt…

Hyperparameter Optimizationmodel

RoseNNa: A performant, portable library for neural network inference with application to computational fluid dynamics

2023-07-30 · Ajay Bati, Spencer H. Bryngelson

The rise of neural network-based machine learning ushered in high-level libraries, including TensorFlow and PyTorch, to support their functionality. Computational fluid dynamics (CFD) researchers have benefited from this…