Interactive Transfer Learning

Transfer learning is the processing of using the outputs of one ML model as an input for a different model.

In this example, I’m using MobileNet image classification results. I’m using a smaller, older version with 256 labels. The data looks like

  { "label": "cat", "value": 0.5 },
  { "label": "dog", "value": 0 }

It surprised me how well it worked to reuse MobileNet for dimensionality reduction. I would’ve thought I would need to retrain a portion of the model.

Next steps:

  • arbitrary chaining of models
  • parallel processing chains
  • retraining models

Andrew Lee lives and works in Brooklyn building data products

Currently Hashboard
Previously Apple, Flatiron Health
NYU ITP Class of 2020


© 2024 Andrew Lee