Jacob Feitelberg

icon indicating a website link jacobf18.github.io

icon company Columbia University icon location New York icon location Ph.D. student in Operations Research at Columbia University. Interests include optimization, control, machine learning, and causal inference.

Results 4 comments of Jacob Feitelberg

How to train own dataset!

I have not tried it yet, and will update this after I've tried it, but the approach that I will take is to convert my data into a classification dataset...

Training on variable-length sequences

Outside of TCN, you can try Dynamic Time Warping to make the sequences the same length.

BIDSification of Winkler et al. dataset and other datasets for training/validation of ICA labeling models

@chmendoza As far as I know, there is no large publicly available dataset for IC classification. We were working on processing a dataset (referenced above) to test the IC classification....

Evaluate and support MEGNet

Looks great. They use tensorflow for their model. Should be easy to convert to ONNX.