Dan Saunders

Weight decay is not affected by simulation (it's set, constant, in advance), so there's no need for anything to change when using minibatching. Also, I've realized a way to implement...

@Huizerd nope, just an idea we had some time ago. I'm not sure that it will speed things up, but it might be worth a shot. Let me know if...

Check out [this branch](https://github.com/Hananel-Hazan/bindsnet/tree/multiprocessing) for a start on the multiprocessing work (I'm pretty sure it fails as-is). It'll need to be fast-forwarded to the current state of the master branch.

Hi @krooq, Thanks for the using BindsNET, and thanks for the feedback! To answer your questions: > Is it worth adding a name attribute to items that can be attached...

@krooq I think I like that idea as well. Could you explain why we might want to move away from strings? Random idea: automatic naming of layers / monitors, for...

> @djsaunde in Python (most other languages) objects have a unique int identifier id(), this is managed by the runtime, I don't think its mutable. It's just more robust and...

That would be awesome!

I'm not sure I agree with your second point. We already have two types of `Nodes`: those that subclass `Nodes` only, and those that subclass both `Nodes` and `AbstractInput`. I...

> The confusion start with the definition of Nodes. Basically, Node have input and output that change according to the input. You can take any node in Nodes (beside the...

> It should be pretty straight forward on the Input side as pytorch supports sparse tensors internally. Yeah, mostly agree except that PyTorch's support for sparse tensor ops is not...