udemirezen Goto Github PK

02456deeplearning_scientificmachinelearning

0_stanford_ml006

0_stanford_ml006_a2

0_Stanford_ML006_A2

0_stanford_ml006_a3

0_stanford_ml006_a4

0_stanford_ml006_a5

1090-insights

Some tools for analyzing the raw CSV output from dump1090 (which logs ADS-B radio packets from airplanes)

1dbloodflowpinns

a-new-convolutional-neural-network-based-data-driven-fault-diagnosis-method

An implemention of paper by GTX 860m and tensorflow

accelerate

A simple way to train and use PyTorch models with multi-GPU, TPU, mixed-precision

acse-9-independent-research-project-oliverjboom

acse-9-independent-research-project-OliverJBoom created by GitHub Classroom

activationfunctions

ada-f

Anti-Derivatives Approximator from Fourier series expansion

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.

admm-pinns

Python codes for the paper "The ADMM-PINNs Algorithmic Framework for Nonsmooth PDE-Constrained Optimization: A Deep Learning Approach"

admm_for_dnn

aeropython

Classical Aerodynamics of potential flow using Python and Jupyter Notebooks

af-classification

Deep Neural Network for Atrial Fibrillation Classification using Tensorflow (For education purpose only)

afraus

unsupervised multi-model fraud-detection algorithm

ai-in-medical-imaging

alibi-detect

Algorithms for outlier, adversarial and drift detection

angularjslivelessons

This is the source code repository to accompany my AngularJS LiveLessons. The code more or less mirrors what I talk about in the videos and demonstrates the key concepts of each lesson and sub-lesson.

animacy-detection

Some experiments with animacy detection in Dutch Folktales

ankus

ANKUS is a deployment & orchestration tool for big data applications

anmin

Analytic Optimization of Two Layer ReLU Networks

ann-visualizer

A python library for visualizing Artificial Neural Networks (ANN)

annarchy

ANNarchy (Artificial Neural Networks architect) is a parallel simulator for rate-coded and spiking neural networks.

antarctic-mapping-tools

Antarctic Mapping Tools for MATLAB functions for analyzing and mapping Antarctic geospatial datasets.

antlr4

apache-mahout-cookbook