Cheap and cheerful neural inference
Add to your list(s)
Download to your calendar using vCal
If you have a question about this talk, please contact Carl Scheffler.
This talk will look at a generative model in which each output unit is connected to a single (possibly different) parent. The task is to infer which output units are connected to the same parent.
This model has the property that all the inference is entirely local, linear and online, which means it could be implemented in a simple model of a neuron.
As this is still a work in progress the talk will only last 30 minutes followed (hopefully) by 15 minutes of discussion.
This talk is part of the Machine Learning Journal Club series.
This talk is included in these lists:
Note that ex-directory lists are not shown.
|