Xilinx uses transmission gates to switch configuration, and transmission gates can also switch analog. Now, if Xilinx would only think of this.
There is an argument that the sorts of bidirectional operation that neurons do might be beyond practical digital simulation, just as some circuits are, because of super sensitive rapid changes in component values. Though AI isn't simulation, it is still up against the same computational challenges. The NN parallel would be things like a need for neurons that suddenly change functionality depending on their effect on downstream neurons. Steve On Thu, Jul 11, 2019, 6:38 PM <[email protected]> wrote: > > > Xilinx Ships Heterogeneous Chips for AI, 5G: > > https://www.eetimes.com/document.asp?doc_id=1334898 > > > > *Artificial General Intelligence List <https://agi.topicbox.com/latest>* > / AGI / see discussions <https://agi.topicbox.com/groups/agi> + > participants <https://agi.topicbox.com/groups/agi/members> + delivery > options <https://agi.topicbox.com/groups/agi/subscription> Permalink > <https://agi.topicbox.com/groups/agi/Te56d98b1cab7ca45-Mce816ce3cb9ed0d08811b258> > ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/Te56d98b1cab7ca45-Mf0d9eb150229ee2d2e0d2f25 Delivery options: https://agi.topicbox.com/groups/agi/subscription
