Thanks Jim.
--
Artificial General Intelligence List: AGI
Permalink:
https://agi.topicbox.com/groups/agi/T4aa81fd9912dbd39-M50559774e050d8b77d141409
Delivery options: https://agi.topicbox.com/groups/agi/subscription
Although the Activation Atlas is a little misleading (in my opinion), it
has given me some vague ideas about how a symbol net might work.
Jim Bromer
On Wed, Mar 13, 2019 at 8:18 PM Jim Bromer wrote:
> Great article. Thanks again.
> Jim Bromer
>
>
> On Tue, Mar 12, 2019 at 6:28 PM wrote:
>
>>
Great article. Thanks again.
Jim Bromer
On Tue, Mar 12, 2019 at 6:28 PM wrote:
>
> Exploring Neural Networks with Activation Atlases:
>
>
>
> https://distill.pub/2019/activation-atlas/?utm_campaign=Data_Elixir_medium=email_source=Data_Elixir_224
> *Artificial General Intelligence List
That is very true Stefan. Detector NN have layers of where simple features are
generally
in the first layers of the NN. And complex feature are detector are in
the later part. There is bit of play in applying the back propagation algorithm
during training
so that complex detection and simple
Hi David
I was paraphrasing what a senior technical representative at Facebook himself
said about the incident. His view was the chatbots developed their own language
and communicated out of scope of the laid-down script. In other words, seems
the door was somehow left open for them to expand
You have a different meaning for "volition" than I do.
The Facebook chatbots had no choice to communicate with each other.
I think the aforementioned communication was a stimulus-response model.
The secret language was just a pattern recognition where signals that had
no
significance replaced
