udemirezen's Stars
mintisan/awesome-kan
A comprehensive collection of KAN(Kolmogorov-Arnold Network)-related resources, including libraries, projects, tutorials, papers, and more, for researchers and developers in the Kolmogorov-Arnold Network field.
IBM/simulai
A toolkit with data-driven pipelines for physics-informed machine learning.
udemirezen/modulus
A PyTorch based deep-learning toolkit for developing DL models for physical systems
NVIDIA/modulus-launch
Repo of optimized training recipes for accelerating PyTorch workflows of AI driven surrogates for physical systems
computational-imaging/bacon
Official respository for "Band-limited Coordinate Networks for Multiscale Scene Representation" | CVPR 2022
udemirezen/cleanlab
The standard package for data-centric AI and machine learning with label errors, finding mislabeled data, and uncertainty quantification. Works with most datasets and models.
udemirezen/scibert
A BERT model for scientific text.
ajayarunachalam/msda
Library for multi-dimensional, multi-sensor, uni/multivariate time series data analysis, unsupervised feature selection, unsupervised deep anomaly detection, and prototype of explainable AI for anomaly detector
cleanlab/cleanlab
The standard data-centric AI package for data quality and machine learning with messy, real-world data and labels.
SeldonIO/alibi-detect
Algorithms for outlier, adversarial and drift detection
reservoirpy/reservoirpy
A simple and flexible code for Reservoir Computing architectures like Echo State Networks
rbischof/relative_balancing
ChrisRackauckas/universal_differential_equations
Repository for the Universal Differential Equations for Scientific Machine Learning paper, describing a computational basis for high performance SciML
barkm/torch-fenics
PyTorch-FEniCS interface
jlager/BINNs
Biologically-informed neural networks
differential-machine-learning/appendices
Complement the article 'Differential Machine Learning' (Huge & Savine, 2020), including mathematical proofs and important implementation details for production
HuHaigen/Adaptively-Customizing-Activation-Functions
To enhance the nonlinearity of neural networks and increase their mapping abilities between the inputs and response variables, activation functions play a crucial role to model more complex relationships and patterns in the data. In this work, a novel methodology is proposed to adaptively customize activation functions only by adding very few parameters to the traditional activation functions such as Sigmoid, Tanh, and ReLU. To verify the effectiveness of the proposed methodology, some theoretical and experimental analysis on accelerating the convergence and improving the performance is presented, and a series of experiments are conducted based on various network models (such as AlexNet, VGGNet, GoogLeNet, ResNet and DenseNet), and various datasets (such as CIFAR10, CIFAR100, miniImageNet, PASCAL VOC and COCO) . To further verify the validity and suitability in various optimization strategies and usage scenarios, some comparison experiments are also implemented among different optimization strategies (such as SGD, Momentum, AdaGrad, AdaDelta and ADAM) and different recognition tasks like classification and detection. The results show that the proposed methodology is very simple but with significant performance in convergence speed, precision and generalization, and it can surpass other popular methods like ReLU and adaptive functions like Swish in almost all experiments in terms of overall performance.
Bellman281/Stat4ML
Statistics and Mathematics for Machine Learning, Deep Learning , Deep NLP
tum-pbs/PhiFlow
A differentiable PDE solving framework for machine learning
biomathlab/PDElearning
Code repository for the paper "Learning partial differential equations for biological transport models from noisy spatiotemporal data"
bayesian-optimization/BayesianOptimization
A Python implementation of global optimization with gaussian processes.
mle-infrastructure/mle-monitor
Lightweight Experiment & Resource Monitoring 📺
marcellodebernardi/loss-landscapes
Approximating neural network loss landscapes in low-dimensional parameter subspaces for PyTorch
idrl-lab/PINNpapers
Must-read Papers on Physics-Informed Neural Networks.
pytorch/functorch
functorch is JAX-like composable function transforms for PyTorch.
adityabalu/DiffNet
DiffNet: A FEM based neural PDE solver package
rocketmlhq/sciml
Scientific Machine Learning Tutorials
CognitiveModeling/finn
The public repository about our joint FINN research project
PML-UCF/pinn_ode_tutorial
ucl-bug/jaxdf
A JAX-based research framework for writing differentiable numerical simulators with arbitrary discretizations