News for hackers. Stuff that matters.
Re:A blog I started on Neural Networks and Probability by partycoder on Thursday November 30, 2017 @11:21AM (#15816947)
Regarding the biology of neurons, it is important to know:

1) that neurons are a family of cells rather than a uniform, homogeneous thing.

2) initially it was believed that dendrites only propagated spikes. now it is accepted that dentrites generate spikes of their own. https://en.wikipedia.org/wiki/Dendritic_spike

3) the concept of threshold has been challenged. eugene izhikevich for example presents some counterexamples for the idea of the threshold (where a spike a spike was expected and doesn't happen, or when a spike was not expected and happens), and provides an alternative explanation involving dynamical systems.

so, while useful, it is important to understand that most artificial neural models are simplified abstractions. eventually we will figure out why biology is doing what is doing. e.g: how much of the biology has to do with information processing, how much of it has to do with keeping neurons alive, and how much of it has to do with passing information around.

Re:A blog I started on Neural Networks and Probability by aisofteng on Thursday November 30, 2017 @05:08PM (#15820041)
What do you mean when you say a neuron is a family of cells?
Re:A blog I started on Neural Networks and Probability by partycoder on Thursday November 30, 2017 @05:24PM (#15820171)
e.g: a pyramidal cell is different from a purkinje cell.
Re:A blog I started on Neural Networks and Probability by aisofteng on Saturday December 02, 2017 @06:08PM (#15834797)
Ah - it sounded like you meant that a neuron consists of more than one cell, not that that there are different types of neurons.