21 skills found
mit-han-lab / TorchquantumA PyTorch-based framework for Quantum Classical Simulation, Quantum Machine Learning, Quantum Neural Networks, Parameterized Quantum Circuits with support for easy deployments on real quantum computers.
sumanth-kalluri / Cnn Hardware Acclerator For FpgaThis is a fully parameterized verilog implementation of computation kernels for accleration of the Inference of Convolutional Neural Networks on FPGAs
flyingdoog / PGExplainerParameterized Explainer for Graph Neural Network
raspstephan / CBRAIN CAMCode for neural network parameterization project
LarsHoldijk / RE ParameterizedExplainerForGraphNeuralNetworksNo description available
eleGAN23 / HyperNetsHypercomplex Neural Networks with PyTorch
dtu-act / Pinn Acoustic Wave PropCode for sound field predictions in domains with impedance boundaries. Used for generating results from the paper "Physics-informed neural networks for 1D sound field predictions with parameterized sources and impedance boundaries" by N. Borrel-Jensen, A. P. Engsig-Karup, and C. Jeong.
WooJin-Cho / Parameterized Physics Informed Neural NetworksNo description available
bayer-science-for-a-better-life / Phc GnnImplementation of the Paper: "Parameterized Hypercomplex Graph Neural Networks for Graph Classification" by Tuan Le, Marco Bertolini, Frank Noé and Djork-Arné Clevert
USCPOSH / AMPSEThis is the repository of IPs of the group in USC who is developing Analog Mixed-signal Parameter Search Engine (AMPSE). You can download IPs generated by AMPSE or parameterized IPs with neural network based parameter-metric regression models. Watch this repository and follow USCPOSH on GitHub for our further updates! USC POSH Group: https://github.com/USCPOSH
noegroup / EDMnetsparameterizing valid Euclidean distance matrices (EDMs) via neural networks
zhangjiong724 / Spectral RNNSTABILIZING GRADIENTS FOR DEEP NEURAL NETWORKS VIA EFFICIENT SVD PARAMETERIZATION
pbalapra / Dl PblFast domain-aware neural network emulation of a planetary boundary layer parameterization in a numerical weather forecast model
JiangBoCS / APD NetsImage denoising methods using deep neural networks have achieved a great progress in the image restoration. However, the recovered images restored by these deep denoising methods usually suffer from severe over-smoothness, artifacts, and detail loss. To improve the quality of restored images, we first propose Supplemental Priors (SP) method to adaptively predict depth-directed and sample-directed prior information for the reconstruction (decoder) networks. Furthermore, the over-parameterized deep neural networks and too precise supplemental prior information may cause an over-fitting, restricting the performance promotion. To improve the generalization of denoising networks, we further propose Regularization Priors (RP) method to flexibly learn depth-directed and dataset-directed regularization noise for the retrieving (encoder) networks. By respectively integrating the encoder and decoder with these plug-and-play RP block and SP block, we propose the final Adaptive Prior Denoising Networks, called APD-Nets. APD-Nets is the first attempt to simultaneously regularize and supplement denoising networks from the adaptive priors’ view with drawing learning-based mechanism into producing adaptive regularization noise and supplemental information. Extensive experiment results demonstrate our method significantly improves the generalization of denoising networks and the quality of restored images with greatly outperforming the traditional deep denoising methods both quantitatively and visually.
DuktigYajie / VGPT PINNEntropy-enhanced Generative Pre-Trained Physics Informed Neural Networks for parameterized nonlinear conservation laws
areeq-hasan / QtransformerqTransformer is a quantum circuit neural network classifier based on chained quantum attention mechanism layers, residual layers, and feed-forward neural network layers. Attention is computed using a trainable, parameterized general two-body interaction between word embedding statevectors in a sentence system; residual connections are represented using CX-gates; feed-forward neural network layers are represented using custom variational ansatzes such as RealAmplitudes and EfficientSU2.
vbelis / Triple EMetrics for Variational Quantum Circuits/Parameterized Quantum Circuits/Quantum Neural Networks.
uwaa-ndcl / Pose Network SensitivityOn the sensitivity of pose estimation neural networks: rotation parameterizations, Lipschitz constants, and provable bounds
Haosen-Zhang / HyperKron MRI ReconOfficial PyTorch implementation of 'Lightweight Hypercomplex MRI Reconstruction: A Generalized Kronecker-Parameterized Approach', leveraging Kronecker-based hypercomplex neural networks for efficient MRI reconstruction. Achieves high-quality MRI reconstruction with significantly fewer parameters, suitable for resource-constrained clinical settings.
nbren12 / UwnetNeural Networks based unified physics parameterization for atmospheric models
