Alex Serenko

[clustering] Possible wrong call of the centroids initializer from the ClusterWeights wrapper

1

An instance of the centroids initializer [expects](https://github.com/tensorflow/model-optimization/blob/v0.7.1/tensorflow_model_optimization/python/core/clustering/keras/clustering_centroids.py#L47) to be initialized with `data_format`. However, instead of `data_format` it gets `num_channels` here: https://github.com/tensorflow/model-optimization/blob/v0.7.1/tensorflow_model_optimization/python/core/clustering/keras/cluster_wrapper.py#L218 I suppose that line is erroneous. This may cause...

In [the weight update rule for pre-after-post spike pairs](https://github.com/zxzhijia/Brian2STDPMNIST/blob/5ccb43b008df1d0324c5ad917a69de1c18a93858/Diehl%26Cook_spiking_MNIST_Brian2.py#L328), there was `-` before `nu_ee_pre` in the original Diehl's code. I am just wondering what the idea behind such change was.

"Thin a wrapper" may have been a misprint. I suggest that it be corrected, as these are the very first words one sees when visiting the page.

Fix Issue #3337

2

The reason of Issue #3337 seems to be just forgotten parentheses.

**Reproduce the bug:** ```python neuron_ids = nest.Create("parrot_neuron", 10) nest.Connect( pre=neuron_ids[:1], # Necessary to reproduce the bug: cast the IDs to a tuple instead of NodeCollection post=neuron_ids[1:].global_id, conn_spec='all_to_all' ) ``` Output:...