On Mon, Jun 11, 2018 at 2:39 PM, MP via AGI <[email protected]> wrote:

> It seems you’re taking a deep learning approach to the classic cognitive
> architectures - like you’re reengineering ACT-R.
>
> What’s different? Why is this any better?
>


​Deep learning's learning algorithm (back-prop / gradient descent) is way
more efficient than classical logic-based learning (based on discrete
combinatorial search inside a *humongous*​ lattice).  Ben Goertzel first
told me that some years ago 😝

------------------------------------------
Artificial General Intelligence List: AGI
Permalink: 
https://agi.topicbox.com/groups/agi/T731509cdd81e3f5f-Mdf1b6da8d994f7e447d3e46a
Delivery options: https://agi.topicbox.com/groups

Reply via email to