The most remarkable thing about the brain is that it wasn't designed. As a result, how the brain works is largely an irrelevant question.
-
It would take billions of years for evolution to come up with modern CPUs, too. It took us humans a few decades. We're pretty efficient.
Would you consider that inspecting the weights values of one convnet is a good way to understand how to train new models on new problems?
-
-
What matters in this case is the training data, hypothesis space, objective, and optimization algorithm. Weight values are a distraction.
-
could you determine what algorithm is running by inspecting a CPU while it operates?
End of conversation
New conversation -
-
-
But in the case of the brain, isn't it the architecture rather than the weights that is of most interest?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
You can analyze the filters learnt by a convnet to design better convnets.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
How does one go about designing a new model? Is the human brain ever a guide? Or don't we know enough about it?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
cultures (read: not bio) evolved complex symbol systems by leveraging specialized mechanisms (read: bio). hard to interface w/o mechanisms
- End of conversation
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.