|
Rajeev
@
rvrikhye
SF Bay Area
|
|
Vision, cognition, AI researcher.
🤖➕🧠➕💻➕👁
Alum of @MIT and @ImperialCollege
Adventurer; Food enthusiast
|
|
|
148
Tweetovi
|
130
Pratim
|
81
Osobe koje vas prate
|
| Tweetovi |
|
Rajeev
@rvrikhye
|
25. pro |
|
Amazing work, congrats @bsauerbrei1!! twitter.com/bsauerbrei1/st…
|
||
|
|
||
| Rajeev proslijedio/la je tweet | ||
|
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
|
||
|
|
||
|
Rajeev
@rvrikhye
|
1. stu |
|
This is cool. ai.googleblog.com/2019/10/learni…
|
||
|
|
||
| Rajeev proslijedio/la je tweet | ||
|
Blake Richards
@tyrell_turing
|
28. lis |
|
1/ SciTwitter: I'm very excited to share our new Perspective article out in Nature Neuroscience today!
nature.com/articles/s4159…
|
||
|
|
||
|
Rajeev
@rvrikhye
|
13. lis |
|
Haha, this is brilliant
medium.com/halting-proble…
|
||
|
|
||
|
Rajeev
@rvrikhye
|
11. lis |
|
These guys have some data too nature.com/articles/nn.37…
|
||
|
|
||
|
Rajeev
@rvrikhye
|
11. lis |
|
Got it. My point really was there is nothing special (statistically or spatially) that you will get from mouse cam movies, except for loads of movement artefacts, unless you want to model optic flow or smth from a rodents perspective.
|
||
|
|
||
|
Rajeev
@rvrikhye
|
11. lis |
|
Basically, replace the Fourier amplitude spectrum of a natural scene with a noise pattern of your choice. Mice love em. jneurosci.org/content/35/43/…
|
||
|
|
||
|
Rajeev
@rvrikhye
|
10. lis |
|
@tyrell_turing I believe Tom Mrsic_Flogel at UCL had some mouse cam movies. Alternatively I have a method to modify the statistics of a natural movie. Published j neuro in 2015. Happy to discuss more.
|
||
|
|
||
|
Rajeev
@rvrikhye
|
1. lis |
|
@missippy congrats
|
||
|
|
||
|
Rajeev
@rvrikhye
|
15. ruj |
|
And that's not including the carbon cost of printing all these posters that will likely only be used once. an archaic practice that has to stop.
|
||
|
|
||
| Rajeev proslijedio/la je tweet | ||
|
Dileep George
@dileeplearning
|
13. ruj |
|
Our 2nd #CCN2019 paper introduces Memorize-Generalize, an algo for fast and flexible learning of sequential structure: it can rapidly memorize sequences as they are encountered, and gradually generalize as more data is accumulated. @vicariousai biorxiv.org/content/10.110… pic.twitter.com/mJ7KgoNKYG
|
||
|
|
||
| Rajeev proslijedio/la je tweet | ||
|
Dileep George
@dileeplearning
|
6. ruj |
|
The preprint of my commentary on 'Building machines that work like the brain' is now on arxiv. It distinguishes between AGI & AUI and uses 'airplanes don't flap wings' as the reason to look to the brain for building #AGI arxiv.org/abs/1909.01561 pic.twitter.com/2O5U1Bvxt4
|
||
|
|
||
| Rajeev proslijedio/la je tweet | ||
|
Tamás Görbe
@TamasGorbe
|
5. kol |
|
A Mathematician's Way* of Converting Miles to Kilometers
• 1 mi ≈ 1.609 km
• The ratio of consecutive Fibonacci numbers Fₙ₊₁/Fₙ tends to the golden ratio φ ≈ 1.618 as n increases
So Fₙ mi ≈ Fₙ₊₁ km
*This is how I do it 😅 pic.twitter.com/Jbuwj6rDC1
|
||
|
|
||
| Rajeev proslijedio/la je tweet | ||
|
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
|
||
|
|
||
|
Rajeev
@rvrikhye
|
7. kol |
|
Fantastic article, highly recommend reading. twitter.com/DeepMind/statu…
|
||
|
|
||
|
Rajeev
@rvrikhye
|
4. kol |
|
@neiltyson ... And the point of this tweet is? Does the data not suggest a need to ban assault weapons. Also aren't the shootings another data point? Utter nonsense. twitter.com/neiltyson/stat…
|
||
|
|
||
| Rajeev proslijedio/la je tweet | ||
|
mardinly
@mardinly
|
18. srp |
|
like what you hear? we are hiring neuroscientists!
jobs.lever.co/neuralink/2fb7…
your biological and technological distinctiveness will be added to our own
|
||
|
|
||
| Rajeev proslijedio/la je tweet | ||
|
Nick Steinmetz
@SteinmetzNeuro
|
16. srp |
|
PUBLIC SERVICE ANNOUNCEMENT: You must cross-validate sorted plots!! E.g. peak-latency sorted colormaps of neural activity. Otherwise you WILL find "sequences" out of random noise. Don't believe me? A proof in four lines. Anyone feel like you have seen the last panel before? pic.twitter.com/Fbb4jLKORE
|
||
|
|
||
| Rajeev proslijedio/la je tweet | ||
|
The Dodo
@dodo
|
6. srp |
|
Imagine if this happened to you 🦍💗 pic.twitter.com/cVruzuvTaJ
|
||
|
|
||