Our book chapter "Cities as Spatial and Social Networks: Towards a Spatio-Socio-Semantic Analysis Framework" is featured by @theAAG Virtual Meeting 2021 and free to download until May 7, 2021. @weiluo0001@GISerXi https://t.co/Or1ytSI8B1
New video: Simulating an epidemic.
What happens when people avoid each other for the most part but still go to a common central location like a store?
What if you can track and isolate cases, but 20% slip through the cracks? 50%?
And much more.
https://t.co/z3ULZWQxPW
I just don’t understand why Zoom is the de facto videoconferencing solution instead of Google Meet or Hangouts or Duo or Allo or Talk or Hangouts Chat or GTalk or Buzz or Wave or Messages or Spaces or Voice or…
I really appreciate the wonderful four years I have had in the lab under a great advisor :) So proud to be one of the first members in @Friendly_Cities lab!
After promising it's coming out in no time for about 2 months. I just published Introducing https://t.co/SqbQgo2asx for Jupyter https://t.co/30mbmJFAeu. Still in beta, give it a try #keplergl@uberEng
Learning embedding space for location?! Turns out the answer is... yes! 🙂
Two absolutely fascinating reads with a lot of good information on approaching DL projects in general.
The first one is a blog post by @sentiance https://t.co/lcXuvhAwio.
1st ACM SIGSPATIAL International Workshop on Spatial Gems (SpatialGems 2019): https://t.co/ETVkCiPztF A very interesting and practically useful theme! Share gems for processing spatial data.
@hardmaru@geoffreyhinton little known fact, the transformer is a close cousin of the capsule network, because soft attention is "routing by agreement".
@JeffDean@TensorFlow Have you seen this rather astonishing work by @citnaj ? (Quite a bit more than 100 lines - but well worth it considering the beautiful results :) )
https://t.co/EInKW7b78W
“A simple novelty search algorithm finds the solution in no time. The issue with standard RL is that they lack good exploration strategies, so if they rely too much on the reward function, they fail miserably.”
Building on prior work training deep RL agents to navigate cities without a map (https://t.co/GjgIL2Ppz4), we can now teach virtual agents to follow navigation instructions in cities #streetlearn
https://t.co/7Ryrx8SjFJ
@karlmoritz@MateuszOnAi @MirowskiPiotr @RaiaHadsell