pytorch-wrapper — Provides a systematic and extensible way to b...
🥀 "We propose a novel deep learning approach for removing systematic batch effects. Our method is based on a residual neural network, trained to minimize the Maximum Mean Discrepancy between the multivariate distributions of two replicates, measured in different batches."
🍂 CK workflow for MILEPOST GCC (machine learning based compiler) to let the community reproduce and build upon our past R&D projects. See related project funded by Raspberry Pi foundation to crowd-tune programs across RPi devices provided by volunteers and apply machine learning (decision trees, deep learning, etc) to acclerate optimization:
🥀 Classification of MNIST digits by convolutional neural networks and then extracting features. After that I tune the to classes labels using simple neural network The code is written using Keras deep learning library. Got Accuracy: %99.82 error rate 0.18
🍂 This repository holds the companion project to Goby3, used to train and evaluate deep learning models to call variations. This repository contains the Matcha framework to help train and evaluate deep learning models trained with semi-simulation. See docs below for details.