News for hackers. Stuff that matters.
Re:Training of Physical Neural Networks by UncleOxidant on Wednesday July 10, 2024 @12:19PM (#40928532)
So it sounds like these PNNs are essentially analog implementations of neural nets? Seems like an odd choice of naming to call them 'physical'.
Re:Training of Physical Neural Networks by tomxor on Wednesday July 10, 2024 @12:59PM (#40928930)
ANN is taken.
Re:Training of Physical Neural Networks by TheLoafOfBread on Wednesday July 10, 2024 @03:17PM (#40930380)
I mean LoRA was taken too before LoRA became a thing
Re:Training of Physical Neural Networks by tomxor on Wednesday July 10, 2024 @04:06PM (#40930965)
I don't mean globally, LoRA are at least in different domains. Artificial Neural Networks and Physical Neural Networks are both machine learning, discussion referring to both is highly probable, and the former far more established so it calling it an Analog Neural Network would never last long.
Re:Training of Physical Neural Networks by TeMPOraL on Thursday July 11, 2024 @01:46AM (#40933982)
You can't call analog NN an AnalNN either, as then the "brain-gut axis" people will throw a fit.
Re:Training of Physical Neural Networks by agarwaen163 on Wednesday July 10, 2024 @07:44PM (#40932567)
Well, this is particularly frustrating because PNN is already taken as well, by the (imo) much more novel idea of Physics Informed Neural Networks (aka PINNs or PNNs).

Why this isn't called Hardware Neural Nets is beyond me.

Re:Training of Physical Neural Networks by pessimizer on Wednesday July 10, 2024 @01:15PM (#40929089)
Makes sense as opposed to "abstract." With the constant encoding and decoding that has to be done when things are going in an out of processors and storage (or sensors), digital processes are always in some sense simulations.