Twitter | Pretraživanje | |
Swaroop Guntupalli
Neuroscientist
44
Tweetovi
133
Pratim
121
Osobe koje vas prate
Tweetovi
Swaroop Guntupalli proslijedio/la je tweet
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"
Swaroop Guntupalli proslijedio/la je tweet
Michael Hanke 7. pro
How is it even possible, now that "AI has taken over", that I buy a washing machine and everything starts recommending me more washing machines? (don't get me wrong: it is a comforting feeling that, outside the movies, not much has happened since Eliza)
Reply Retweet Označi sa "sviđa mi se"
Swaroop Guntupalli proslijedio/la je tweet
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"
Swaroop Guntupalli proslijedio/la je tweet
Michael Hanke 6. pro
Great interview, in which the man himself explains how he manages to get an infinite amount of work done in the same finite time that the rest of us have ;-) thx !
Reply Retweet Označi sa "sviđa mi se"
Swaroop Guntupalli proslijedio/la je tweet
Dileep George 13. ruj
Odgovor korisniku/ci @rvrikhye @swaroopgj
It also learns a lossy compressed graph representation of the underlying sequences. Closely related to our 1st paper on cognitive maps as higher-order sequences.
Reply Retweet Označi sa "sviđa mi se"
Swaroop Guntupalli 5. ruj
Insightful commentary from
Reply Retweet Označi sa "sviđa mi se"
Swaroop Guntupalli proslijedio/la je tweet
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"
Swaroop Guntupalli proslijedio/la je tweet
Surya Ganguli 18. srp
1/ New in w/ lab: : new opsin + multi-photon holography to image ~4000 cells in 3D volumes over 5 cortical layers while also stimulating ~50 neurons to directly drive visual percepts; data analysis and theory reveal…
Reply Retweet Označi sa "sviđa mi se"
Swaroop Guntupalli proslijedio/la je tweet
Dileep George 7. svi
Thread about our new paper on learning the structure of variable order sequences. Imposing a biologically-inspired sparsity structure alleviates the credit diffusion problem in HMMs! Also relevant for neuroscience... (1)
Reply Retweet Označi sa "sviđa mi se"
Swaroop Guntupalli proslijedio/la je tweet
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"
Swaroop Guntupalli proslijedio/la je tweet
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"
Swaroop Guntupalli proslijedio/la je tweet
Dileep George 17. sij 2019.
Mini thread about the cognitive science and neuroscience inspirations behind our new paper in which we learn concepts as 'cognitive programs' on a 'visual cognitive computer'.
Reply Retweet Označi sa "sviđa mi se"
Swaroop Guntupalli proslijedio/la je tweet
News from Science 16. sij 2019.
Instead of relying on a list or rules, a new computational framework for learning lets robots come up with their own concepts by detecting abstract differences in images and then recreating them in real life:
Reply Retweet Označi sa "sviđa mi se"
Swaroop Guntupalli proslijedio/la je tweet
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"
Swaroop Guntupalli proslijedio/la je tweet
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"
Swaroop Guntupalli proslijedio/la je tweet
Steven Strogatz 18. ruj 2018.
What a gift! Ramanujan’s papers, now online.
Reply Retweet Označi sa "sviđa mi se"
Swaroop Guntupalli proslijedio/la je tweet
Rodney Brooks 11. ruj 2018.
Moore's law sputtering to an end. Now is the time for new architectures and creativity!
Reply Retweet Označi sa "sviđa mi se"
Swaroop Guntupalli proslijedio/la je tweet
Sam Nastase 11. ruj 2018.
New paper with , , and ! Hyperalignment factors out idiosyncrasies in functional–anatomical correspondence, revealing individual differences in fine-grained functional architecture otherwise obscured by anatomical normalization
Reply Retweet Označi sa "sviđa mi se"
Swaroop Guntupalli proslijedio/la je tweet
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"
Swaroop Guntupalli proslijedio/la je tweet
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"