-
```
Neurons in beings' minds group into subsystems that are visible to other
groups as single neurons. You can see it as a modularization. This is
something that is not present in aForge and would be …
-
1. During the update of weights, you directly assign the gradients to the weights.
2. The training process is wrongly implemented. The original paper uses forward neuron states to train generative we…
-
All of them are currently for LIF neurons, which is an oversight if we have the IZH model working.
-
Converting the loaded model using to_neuron() method takes a long time. Is there any way to Save the neuron_model on disk and load it again? This is for GPT-NeoX.
-
There are some models of unsupervised synaptic plasticity that are thought of as the neurons trying to adjust their parameters such that they fire a certain proportion of the time. This is sometimes …
-
In QNNs we sometimes get "dead neurons" (for FC layers) or "dead channels" (for conv layers). Sometimes the output from the dot product is always guaranteed to fall within a certain range that corresp…
-
With the advent of virtual nodes, the nodes created by user are no longer correlated with the cable of the reconstructed neurons. The easiest is to change the pie chart and listings to show cable, usi…
-
Traditionally we have releases under https://neuron.yale.edu/ftp/neuron/versions/v7.6/. May be we can also start tagging releases on GitHub so that we can use those for packaging softwares?
-
-
It would be incredibly powerful if neuroglancer supported simple non-rigid transforms like thin plate spline transforms from user-provided landmarks (via CSV/URL).
Possible applications:
- co-vis…