Name: Stella Sangyoon Bae
Type: User
Company: SNU Connectome Lab
Bio: Ph.D. student, Interdisciplinary program in Artificial Intelligence, SNU.
Loves developing foundation model for neuroimage and bio-inspired AI with curiosity.
Twitter: StellaSYBae
Location: Seoul
Stella Sangyoon Bae's Projects
Code repo for Attend and Decode: 4D fMRI Task State Decoding Using Attention Models, https://arxiv.org/abs/2004.05234
GIRE basic python course sample github repository
A high-level toolbox for using complex valued neural networks in PyTorch
DeepSpeed is a deep learning optimization library that makes distributed training easy, efficient, and effective.
dFCwalk toolbox for dynamic Functional Connectivity analyses in terms of random walk descriptions, by Arbabyazd et al. (2020). MATLAB implementation
Python package built to ease deep learning on graph, on top of existing DL frameworks.
Anomaly detection with diffusion models
Deep Learning Model for Signal Data
Implementation of f-AnoGAN with PyTorch
Basic python course in GIRE
Graph Transformer Networks (Authors' PyTorch implementation for the NeurIPS 19 paper)
This is the official implementation for "Do Transformers Really Perform Bad for Graph Representation?".
Instant neural graphics primitives: lightning fast NeRF and more
Many studies have shown that the performance on deep learning is significantly affected by volume of training data. The MedicalNet project provides a series of 3D-ResNet pre-trained models and relative code.
MemAE for anomaly detection. -- Gong, Dong, et al. "Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection". ICCV 2019.
SNU 2021 Fall MLVU final project
A Python package to facilitate the development, parallel simulation, optimization and analysis of multiscale biological neuronal networks in NEURON.
object centric LVDM
Benchmark datasets, data loaders, and evaluators for graph machine learning
term project for PGM 2022
PrediXcan Project
Tool for producing high quality forecasts for time series data that has multiple seasonality with linear or non-linear growth.
Portfolio and risk analytics in Python
Tutorials on implementing a few sequence-to-sequence (seq2seq) models with PyTorch and TorchText.