QuadraLib: A Performant Quadratic Neural Network Library for Architecture Optimization and Design Exploration
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
TorchFL: A Performant Library for Bootstrapping Federated Learning Experiments
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 Learningfrax: Fast Robot Kinematics and Dynamics in JAX
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
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 ClassificationFlexible Differentiable Optimization via Model Transformations
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 OptimizationmodelRoseNNa: A performant, portable library for neural network inference with application to computational fluid dynamics
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…