Live data from Hacker News

Understanding the role of individual units in a deep neural network

pnas.org

1–7 of 7 posts

Re: Understanding the role of individual units in a deep neural network

#3
post #2

Perturbing units and observing change is so much like the early days of neurology and neuroscience. Lesion studies in post-surgery patients or those with stroke or brain damage told us a lot, removing part of the circuit and observing what changed.

yup. i remember reading about something called ‘optimal brain damage’ which aims at pruning non-essential weights from the network for faster training etc.

Re: Understanding the role of individual units in a deep neural network

#4
We also think there should be more Ablation Studies in deep learning research. To make it easier, we are working on automating the process of disabling components of models with a framework called Maggy. Pass in your Keras Model and specify which layes/components to mask out and we will generate all models and train them in parallel. https://databricks.com/session_eu20/parallel-ablation-studie... https://github.com/logicalclocks/maggy

Re: Understanding the role of individual units in a deep neural network

#6
This is all super cool, but for those of you who tl:dr;ed, check out their application - creating a "concept painting" app. You can literally click "door" and spray on the picture, and it'll put a door there for you.

http://gandissect.csail.mit.edu

http://gandissect.res.ibm.com/ganpaint.html?project=churchou...