The neural network is 100s of billions of nodes that are connected to each other with connections of different strengths or “weights”, just like our neurons. Open source weights means that they released the weight of connections between the nodes, the blueprint of the neural network, if you will. It is not open source because they didn’t release the material that it was trained on.
There are probably several “mnist” or other smaller networks that are fully open sourced. But that’s not the kind of neural networks most are talking about.
The neural network is 100s of billions of nodes that are connected to each other with connections of different strengths or “weights”, just like our neurons. Open source weights means that they released the weight of connections between the nodes, the blueprint of the neural network, if you will. It is not open source because they didn’t release the material that it was trained on.
Thanks.
Are there any models that are truly open source where they have shown the datasets it was trained on?
There are probably several “mnist” or other smaller networks that are fully open sourced. But that’s not the kind of neural networks most are talking about.
Not that I know of
I’m not sure if I’m missing a definition here but open source usually means that anyone can use the source code under some or no conditions.
You can’t use the source code, just the neural network the source code generated.
deleted by creator
I’m pretty sure open source means that the source code is open to see. I’m pretty sure there is open source things that you need to pay to use.
Open source means bx definition that the code is open the usage is open and anybody can use it.
This includes in theory the training material for the model.
But in common language open source means: i can download it and it runs on my machine. Ignoring legal shit.