Spandan Madan
@spandan_madanML researcher with an interest in Neuroscience.
Similar User
@lilianweng
@fredodurand
@aditimavalankar
@phillip_isola
@agarwl_
@StefanoErmon
@akanazawa
@adityagrover_
@imankitgoyal
@poolio
@j_foerst
@FrancescoLocat8
@drsrinathsridha
@jiajunwu_cs
@alexisjross
Humans easily recognize new objects in unseen poses, but can CNNs? Our work in Nature Machine Intelligence explores when and how CNNs generalize to out-of-distribution (OOD) category-viewpoint combinations, and the neural mechanism driving generalization: rdcu.be/cHynz.
Amazing work on the foundations of how language is represented in the human brain!
Initial steps towards understanding how the brain processes language. Graduate student Pranav Misra discovered a remarkably invariant representation of parts of speech in the human brain. See article here: klab.tch.harvard.edu/publications/P…
Racing🚴♂️100km to fundraise for improving economic mobility for marginalized people in Boston! Need to raise $250 as a part of my fundraising commitment. Please consider donating: secure.qgiv.com/event/bike-a-t…
Chandrayaan-3 Mission: 'India🇮🇳, I reached my destination and you too!' : Chandrayaan-3 Chandrayaan-3 has successfully soft-landed on the moon 🌖!. Congratulations, India🇮🇳! #Chandrayaan_3 #Ch3
#MITTeachMeSomething The Checkershadow Illusion Jaykishan Patel, Ph.D in Brain Behavior and Cognitive Sciences, York University Want to learn more? teachmesomething.mit.edu/tms/checkersha… #illusion #opticalillusion #checkershadowillusion #perception #vision #brain
What will happen first---Solving AGI, or Conda's Solving Environment?
A History of the World in 13 Short Poems: 1. Sappho, sometimes called the Tenth Muse, was an Ancient Greek poet who lived in the 6th century BC. All we have left of her work are incomplete, tantalising fragments. Fragment 147 I tell you someone will remember us in the future.…
First research paper (preprint) from the lab🙌 Work with @stothe2 We explore the cell-type specific variances in the “linking hypotheses” relating IT cortex and object recognition behavior.Most ANN representations are a bit more like Exc than Inh neurons. biorxiv.org/content/10.110…
Approach only used the turning technique that is not novel. Lack novelty. Strong Reject. #NeurIPS
PhD “students” instead of employees. And @oatly being healthy.
I am looking forward to the replies on this one. 🤣
In 1922, a team of scientists went to the Toronto General Hospital, where numerous children with diabetes - often upwards of 50 - were housed in wards. Most of these children were in diabetic comas. In what can only be described as their deathbeds, these children were waiting…
This is the funniest thing I've seen in a long time 😭
Arthur Schopenhauer on avoiding the Current Thing:
ML Reviewer does not know PAC learning.
3% of Britons have “never heard” of the United States.
New data point for why a war on woke might not have the cut through proponents assume. Despite a barrage of criticism for the National Trust for ‘going woke’ - 72% of Brits say it is a force for good, just 7% a force for bad. A higher net good score than the Royal British Legion
Here's an animation of a @PyTorch DataLoader. It turns your dataset into a shuffled, batched tensors iterator. (This is my first animation using @manim_community, the community fork of @3blue1brown's manim) Here's a little summary of the different parts for those curious: 1/5
In the LLM-science discussion, I see a common misconception that science is a thing you do and that writing about it is separate and can be automated. I’ve written over 300 scientific papers and can assure you that science writing can’t be separated from science doing. Why? 1/18
Reject, Revise, Resubmit, (Rinse &) Repeat.
Thrilled to announce I have no clue what LLAMA-2 is, and absolutely no clue why every tweet advertises # of Billion Parameters.
#MITTeachMeSomethingTuesday The Ponzo Illusion Kohitij Kar, Assistant Professor, York University; Canada Research Chair in Visual Neuroscience; Visiting Scientist, MIT Want to learn more? teachmesomething.mit.edu/tms/ponzo-illu… #opticalillusion #vision #brain #PonzoIllusion #ponzo
United States Trends
- 1. Chiefs 146 B posts
- 2. #SmackDown 24,3 B posts
- 3. Georgia Tech 4.155 posts
- 4. Shinsuke 2.939 posts
- 5. Jeanty 22,8 B posts
- 6. Mahomes 29,9 B posts
- 7. Haynes King N/A
- 8. Heisman 26,4 B posts
- 9. Arian Smith N/A
- 10. Iowa 14,9 B posts
- 11. Brock Bowers 9.376 posts
- 12. Andrade 8.246 posts
- 13. Antonio Pierce 2.220 posts
- 14. Myles Colvin N/A
- 15. #loveafterlockup N/A
- 16. Bobo 39,5 B posts
- 17. #LVvsKC 10,2 B posts
- 18. #GoDawgs 3.267 posts
- 19. Zelensky 104 B posts
- 20. Carlson 19,2 B posts
Who to follow
-
Lilian Weng
@lilianweng -
Fredo Durand
@fredodurand -
Aditi Mavalankar
@aditimavalankar -
Phillip Isola
@phillip_isola -
Rishabh Agarwal
@agarwl_ -
Stefano Ermon
@StefanoErmon -
Angjoo Kanazawa
@akanazawa -
Aditya Grover
@adityagrover_ -
Ankit Goyal
@imankitgoyal -
Ben Poole
@poolio -
Jakob Foerster
@j_foerst -
Francesco Locatello
@FrancescoLocat8 -
Srinath Sridhar
@drsrinathsridha -
Jiajun Wu
@jiajunwu_cs -
Alexis Ross
@alexisjross
Something went wrong.
Something went wrong.