Twitter | Pretraživanje | |
Vicarious
AI for the robot age®
30
Tweetovi
0
Pratim
2.588
Osobe koje vas prate
Tweetovi
Vicarious 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.
Reply Retweet Označi sa "sviđa mi se"
Vicarious 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.
Reply Retweet Označi sa "sviđa mi se"
Vicarious 27. kol
Our 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.
Reply Retweet Označi sa "sviđa mi se"
Vicarious 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!
Reply Retweet Označi sa "sviđa mi se"
Vicarious 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.
Reply Retweet Označi sa "sviđa mi se"
Vicarious proslijedio/la je tweet
Science Robotics 31. sij 2019.
ICYMI: This gripper processes data from a schematic visual, predicts the effect of imagined movements and writes those results onto an “ blackboard,” and finally, transforms its imagination into action via from :
Reply Retweet Označi sa "sviđa mi se"
Vicarious proslijedio/la je tweet
Samsung NEXT 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
Reply Retweet Označi sa "sviđa mi se"
Vicarious 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.
Reply Retweet Označi sa "sviđa mi se"
Vicarious 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.
Reply Retweet Označi sa "sviđa mi se"
Vicarious 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.
Reply Retweet Označi sa "sviđa mi se"
Vicarious proslijedio/la je tweet
Matt Turck 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 co-founder (who has the coolest AI Twitter handle)
Reply Retweet Označi sa "sviđa mi se"
Vicarious 13. stu 2018.
Some common sense about common sense. Very much worth the read and not just because we are in it.
Reply Retweet Označi sa "sviđa mi se"
Vicarious 6. stu 2018.
Great shoutout to our SchemaNets paper in Melanie Mitchell's thoughtful article on the current state of AI.
Reply Retweet Označi sa "sviđa mi se"
Vicarious 7. kol 2018.
Odgovor korisniku/ci @vicariousai
Here are the links to our CNN-18 papers: Cortical Microcircuits from a Generative Vision Model: Explaining Visual Cortex Phenomena using Recursive Cortical Network:
Reply Retweet Označi sa "sviđa mi se"
Vicarious 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.
Reply Retweet Označi sa "sviđa mi se"
Vicarious 6. lip 2018.
Mathew Hutson's '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!
Reply Retweet Označi sa "sviđa mi se"
Vicarious proslijedio/la je tweet
St. Gallen 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
Reply Retweet Označi sa "sviđa mi se"
Vicarious proslijedio/la je tweet
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!
Reply Retweet Označi sa "sviđa mi se"
Vicarious 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.
Reply Retweet Označi sa "sviđa mi se"
Vicarious 7. velj 2018.
Learning concepts through sensorimotor interactions is important for general AI. Check out our AAAI18 paper and blog on this topic:
Reply Retweet Označi sa "sviđa mi se"