Name: Hossein Sharifi-Noghabi
Type: User
Company: Borealis AI
Bio: Machine Leaning Researcher @ Borealis AI, PhD in Computer Science @ SFU, interested in applied research.
Twitter: Hossein_SHN
Location: Vancouver, Canada
Blog: https://hosseinshn.github.io
Hossein Sharifi-Noghabi's Projects
A repository for Adversarial Inductive Transfer Learning with input and output space adaptation
This is a repository for Multi-task learning with toy data in Pytorch and Tensorflow
A sensitive and fast tool for circular RNA detection from RNA-Seq data
This repository is created for some codes, files, and supplementary materials for Deep Genomic Signature for early metastasis prediction in prostate cancer.
DGSML is the first method of semi-supervised meta learning that employs two novel loss functions to learn a predictive domain-invariant representation by taking both labeled and unlabeled samples from different input domains
This in my Demo of Chen et al. "GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks" ICML 2018
:sparkles: Build a beautiful and simple website in literally minutes. Demo at http://deanattali.com/beautiful-jekyll
MOLI: Multi-Omics Late Integration with deep neural networks for drug response prediction
Velodrome combines semi-supervised learning and out-of-distribution generalization (domain generalization) for drug response prediction and pharmacogenomics