Eric: Good article in the right direction.
Timothy Busbice
41

First, I’m a fan of your work. I’m excited to see your comment. I’m very interested in following your work on artificial connectomes.

“Firstly, computer neural networks (DNNs, CNNs, ANNs, etc) are nothing like the way the brain or neurons work.”

I believe I made that clear near the bottom of the article, following the description of the simplified math used in lots of computer neural nets:

“As I’ve described above, real neurons don’t behave that way.”

The purpose of this series is to explore different ways to model neuron-like behavior in computers, not to explain how existing models work, nor imply that existing models model biology accurately. I should probably make the scope and purpose more clear in the introduction.

There is a part 2, but sadly, readership for part 2 was extremely low, which impacts my resources available to continue working on the series. I hope I’ll have a chance to pick it up again in the future, but for now I’ve had to put it on the back burner.

One clap, two clap, three clap, forty?

By clapping more or less, you can signal to us which stories really stand out.