Challenges in data labels
Published:
I here list some different challenges in data labels that I encountered in the past and ways to model them.
Posts by Tags
Challenges in data labels
Communities detection
Notes from reading papers on SBM and GNN
Published:
Notes from reading papers about Stochastic Block Models and Graph Neural Networks
Cosine similarity
OMP for sparse signal recovery
Published:
Ortogonal Matching Pursuit for recovering sparse signals
Electrodermal Activity
Wearable EDA Quality Model improves SOTA
Published:
Improve Electrodermal activity (EDA) signal quality SOTA by $8\%$ by unsupervised pre-training
Graph Neural Networks
Notes from reading papers on SBM and GNN
Published:
Notes from reading papers about Stochastic Block Models and Graph Neural Networks
LSTM
Predict unit-level LoS using time-series modelling
Published:
We propose to a dynamic, real-time, lightweight, end-to-end next day median ED-LoS prediction algorithm using time-series LSTM modelling. Similar method can be extended to unit-level KPI prediction.
MTL&MML
Multi-task learning and Multi-Modal learning
Published:
Multi-task Learning solves multiple tasks at one time, while exploiting commonalities and differences across tasks. Multi-modal Learning integrates and processes multiple types of data in one framework.
Motion Artifacts
Wearable EDA Quality Model improves SOTA
Published:
Improve Electrodermal activity (EDA) signal quality SOTA by $8\%$ by unsupervised pre-training
Multi-Modal Learning (MML)
Multi-task learning and Multi-Modal learning
Published:
Multi-task Learning solves multiple tasks at one time, while exploiting commonalities and differences across tasks. Multi-modal Learning integrates and processes multiple types of data in one framework.
Multi-Task Learning (MTL)
Multi-task learning and Multi-Modal learning
Published:
Multi-task Learning solves multiple tasks at one time, while exploiting commonalities and differences across tasks. Multi-modal Learning integrates and processes multiple types of data in one framework.
Signal processing
OMP for sparse signal recovery
Published:
Ortogonal Matching Pursuit for recovering sparse signals
Sparsity ML
OMP for sparse signal recovery
Published:
Ortogonal Matching Pursuit for recovering sparse signals
Stochastic Block Models
Notes from reading papers on SBM and GNN
Published:
Notes from reading papers about Stochastic Block Models and Graph Neural Networks
Unsupervised Pre-Train
Wearable EDA Quality Model improves SOTA
Published:
Improve Electrodermal activity (EDA) signal quality SOTA by $8\%$ by unsupervised pre-training
Wearables
Wearable EDA Quality Model improves SOTA
Published:
Improve Electrodermal activity (EDA) signal quality SOTA by $8\%$ by unsupervised pre-training
Windows
Automatic python script start setup
Published:
A simple tutorial on how to host a python service on a server using bat script and task scheduler.
audio signal processing
Tutorial for audio MNIST dataset
Published:
This is a tutorial for analyzing audio MNIST (digits) dataset
automatic start
Automatic python script start setup
Published:
A simple tutorial on how to host a python service on a server using bat script and task scheduler.
bat
Automatic python script start setup
Published:
A simple tutorial on how to host a python service on a server using bat script and task scheduler.
category1
Chat-GPT assists programming and debugging
Published:
How Chat-gpt from Open-AI going to affect our day-to-day work?
category2
Chat-GPT assists programming and debugging
Published:
How Chat-gpt from Open-AI going to affect our day-to-day work?
classification
Tutorial for audio MNIST dataset
Published:
This is a tutorial for analyzing audio MNIST (digits) dataset
clustering
Time series clustering using tslearn
Published:
TSlearn package for classic timeseries clustering methods.
contrastive learning
notes for deep one-class classification
Published:
Notes for reading paper: learning and evaluating representations for deep one-class classification link.
cool posts
Chat-GPT assists programming and debugging
Published:
How Chat-gpt from Open-AI going to affect our day-to-day work?
dynamic time wrapping
Time series clustering using tslearn
Published:
TSlearn package for classic timeseries clustering methods.
gradient zero crossings
Reverse gradient searching for turning point
Published:
This note summerizes using a simple and efficient trick: reverse gradient searching for finding turning points in noisy cases.
k-means
Time series clustering using tslearn
Published:
TSlearn package for classic timeseries clustering methods.
one-class classification
notes for deep one-class classification
Published:
Notes for reading paper: learning and evaluating representations for deep one-class classification link.
predictive model
Predict unit-level LoS using time-series modelling
Published:
We propose to a dynamic, real-time, lightweight, end-to-end next day median ED-LoS prediction algorithm using time-series LSTM modelling. Similar method can be extended to unit-level KPI prediction.
signal processing
Reverse gradient searching for turning point
Published:
This note summerizes using a simple and efficient trick: reverse gradient searching for finding turning points in noisy cases.
task scheduler
Automatic python script start setup
Published:
A simple tutorial on how to host a python service on a server using bat script and task scheduler.
time series
Predict unit-level LoS using time-series modelling
Published:
We propose to a dynamic, real-time, lightweight, end-to-end next day median ED-LoS prediction algorithm using time-series LSTM modelling. Similar method can be extended to unit-level KPI prediction.
Time series clustering using tslearn
Published:
TSlearn package for classic timeseries clustering methods.
turning points detection
Reverse gradient searching for turning point
Published:
This note summerizes using a simple and efficient trick: reverse gradient searching for finding turning points in noisy cases.
unit-level Length of Stay(LoS)
Predict unit-level LoS using time-series modelling
Published:
We propose to a dynamic, real-time, lightweight, end-to-end next day median ED-LoS prediction algorithm using time-series LSTM modelling. Similar method can be extended to unit-level KPI prediction.
unsupervised learning
notes for deep one-class classification
Published:
Notes for reading paper: learning and evaluating representations for deep one-class classification link.