| Tweetovi |
|
Vicarious
@vicariousai
|
7. pro |
|
You'd think a generative model should answer different queries but deep learning models like VAEs are trained to answer just one type of query! We introduce a method called query-training that creates an inference network that can answer novel query types. openreview.net/pdf?id=rJeoKJ3… pic.twitter.com/SVR0kxpwQJ
|
||
|
|
||
|
Vicarious
@vicariousai
|
6. pro |
|
We show that a singular principle of variable-order sequence learning in a structured model can explain cognitive maps phenom: spatial maps, transitive inference, temporal order, hierarchical planning, remapping etc. -- all important for AI & neuroscience. biorxiv.org/content/10.110… pic.twitter.com/k8guF87lEB
|
||
|
|
||
|
Vicarious
@vicariousai
|
27. kol |
|
Our #CCN2019 paper proposes a new model for cognitive maps in the hippocampus which involves learning higher-order graphs of event sequences. It can explain flexible planning, route-dependence of place cells, and subsumes successor representations. biorxiv.org/content/10.110… pic.twitter.com/KASM6l6RBK
|
||
|
|
||
|
Vicarious
@vicariousai
|
7. lip |
|
Deep learning is contributing to climate change: one more reason to develop data-efficient 'green' learning algorithms as we do at Vicarious! Small data for the win! technologyreview.com/s/613630/train…
|
||
|
|
||
|
Vicarious
@vicariousai
|
6. svi |
|
If yuor laugnage moedl cnnaot raed tihs, it mgiht not be vrey dnagorues 😜. See our paper on learning graphs that can model higher-order sequences and deal with uncertainty. arxiv.org/abs/1905.00507 pic.twitter.com/b1bHNZ7Om4
|
||
|
|
||
| Vicarious proslijedio/la je tweet | ||
|
Science Robotics
@SciRobotics
|
31. sij 2019. |
|
ICYMI: This gripper #robot processes data from a schematic visual, predicts the effect of imagined movements and writes those results onto an “#imagination blackboard,” and finally, transforms its imagination into action via #AI from @vicariousai: bit.ly/2Rts1DK pic.twitter.com/arMFhsQAMh
|
||
|
|
||
| Vicarious proslijedio/la je tweet | ||
|
Samsung NEXT
@SamsungNEXT
|
27. sij 2019. |
|
“Even when you try to teach robots by demonstration, they’re just repeating the exact same motions you show them, not the concept underlying them,” Dileep George with @vicariousai #AI sciencenews.org/article/new-ro…
|
||
|
|
||
|
Vicarious
@vicariousai
|
22. sij 2019. |
|
A thought is a program! Check out our blog to see how we are building a cognitive architecture towards AGI. Also included: code, data, and a free link to our recent Science Robotics paper on concept learning. vicarious.com/2019/01/18/a-t…
|
||
|
|
||
|
Vicarious
@vicariousai
|
16. sij 2019. |
|
Our concept-learning work is now published in Science Robotics! Checkout this very nice video that Science made to explain the paper. twitter.com/NewsfromScienc…
|
||
|
|
||
|
Vicarious
@vicariousai
|
10. pro 2018. |
|
Our new paper learns concepts as programs on a 'visual cognitive computer', showing zero-shot task-transfer on robots, and strong generalization. We bring cogsci ideas about perceptual symbol systems and image schemas into the realm of machine learning. arxiv.org/abs/1812.02788 pic.twitter.com/wkKrPe8CZA
|
||
|
|
||
| Vicarious proslijedio/la je tweet | ||
|
Matt Turck
@mattturck
|
27. stu 2018. |
|
“AI has a common sense problem.” Getting from narrow AI to general AI will involve flipping the paradigm and efficiently learning from a small dataset, the way a human does, says @vicariousAI co-founder @dileeplearning (who has the coolest AI Twitter handle) #DataDrivenNYC pic.twitter.com/geJFRU3u4N
|
||
|
|
||
|
Vicarious
@vicariousai
|
13. stu 2018. |
|
Some common sense about common sense. Very much worth the read and not just because we are in it. twitter.com/WIRED/status/1…
|
||
|
|
||
|
Vicarious
@vicariousai
|
6. stu 2018. |
|
Great shoutout to our SchemaNets paper in Melanie Mitchell's thoughtful article on the current state of AI. twitter.com/MelMitchell1/s…
|
||
|
|
||
|
Vicarious
@vicariousai
|
7. kol 2018. |
|
Here are the links to our CNN-18 papers:
Cortical Microcircuits from a Generative Vision Model: biorxiv.org/content/early/…
Explaining Visual Cortex Phenomena using Recursive Cortical Network: biorxiv.org/content/early/…
|
||
|
|
||
|
Vicarious
@vicariousai
|
7. kol 2018. |
|
Checkout our CCN-18 papers! (1) RCN-derived circuits suggest precise functional roles for feed-forward, feedback, and lateral connections, and for the thalamus. (2) RCN can explain multiple visual phenomena including two well-known illusions. #CCN18 #microcircuits pic.twitter.com/HfoKoHIscT
|
||
|
|
||
|
Vicarious
@vicariousai
|
6. lip 2018. |
|
Mathew Hutson's @silverjacket's wonderfully researched feature in Science is worth a read. The article explores how AI can learn more like humans and highlights research at Vicarious! sciencemag.org/news/2018/05/h…
|
||
|
|
||
| Vicarious proslijedio/la je tweet | ||
|
St. Gallen Symposium
@SG__Symposium
|
4. svi 2018. |
|
“Regulation has always a part in society to ensure that companies do not externalise their costs. Governments have a critical role in this context.” Dileep George @vicariousai #48sgs #beyondwork #futureworkforce #nextgeneration pic.twitter.com/hugiVHdkeL
|
||
|
|
||
| Vicarious proslijedio/la je tweet | ||
|
PBS
@PBS
|
30. tra 2018. |
|
Missed Bill Gates and Scott Phoenix's interviews on last Friday's episode of In Principle? Catch up and stream it now! #InPrincipleOnPBS to.pbs.org/2FvaYWY
|
||
|
|
||
|
Vicarious
@vicariousai
|
26. tra 2018. |
|
Keep an eye out for Scott on the newest installment of PBS's In Principle. The episode also features Bill Gates (!!!) and airs tomorrow night at 8:30. #InPrincipleOnPBS bit.ly/ScottPhoenix2
|
||
|
|
||
|
Vicarious
@vicariousai
|
7. velj 2018. |
|
Learning concepts through sensorimotor interactions is important for general AI. Check out our AAAI18 paper and blog on this topic: vicarious.com/2018/02/07/lea…
|
||
|
|
||