
Ansh Soni
@Ansh_soni1234
Followers
112
Following
289
Media
4
Statuses
32
RT @KordingLab: Why (partial) human connectomes without molecules probably are not all that useful for AI.
0
6
0
RT @neocentrist: You're all wrong. Autism is caused by inflation (R^2 of 0.976). And to be clear, NGDP targeting would fix this. https://….
0
2K
0
RT @ArtDeza: @saranormous Because there really isn't an AGI recipe. This is something that the rigor of academia thankfully puts perspectiv….
0
1
0
RT @AToliasLab: After 7 years, thrilled to finally share our #MICrONS functional connectomics results!. We recorded activity from ~75K neur….
0
95
0
RT @KordingLab: Massive scale product (>1000 babies) diagnosing CP from videos: by @quietscientific.
medrxiv.org
Cerebral Palsy (CP) is a common (about 1 in 500 children) health condition caused by abnormal brain development that affects the ability to control movement. Early risk assessment happens through the...
0
3
0
RT @nacloos: ⁉️What do model-neural similarity scores tell us?. To systematically explore this for different metrics, we develop new numeri….
0
61
0
RT @Ansh_soni1234: @aran_nayebi @jeffrey_bowers @RylanSchaeffer Hi @aran_nayebi, just wanted to clarify that the paper @jeffrey_bowers has….
0
3
0
I think this is the clearest takeaway. We can see that the ranking across different models is not consistent between different measures. Here's a plot from (bit of a shameless plug) highlighting the inconsistency.
Apropros of nothing, I would like to say that we should NOT be using metrics to rank order neural network models from best to worst. We should be using metrics to make predictions, find clusters of models, etc. Triangle inequality is the antidote to Goodharting. Details 👇.
1
3
24
RT @meenakshik93: While I don’t agree with everything, the paper raises an important issue about linear predictivity's limitations. Another….
openreview.net
Neuroscience and artificial intelligence (AI) both face the challenge of interpreting high-dimensional neural data, where the comparative analysis of such data is crucial for revealing shared...
0
5
0
RT @NobelPrize: The 2024 #NobelPrize laureates in chemistry Demis Hassabis and John Jumper have successfully utilised artificial intelligen….
0
4K
0
RT @NobelPrize: BREAKING NEWS.The Royal Swedish Academy of Sciences has decided to award the 2024 #NobelPrize in Physics to John J. Hopfiel….
0
13K
0
Upshot: we need to care about the metrics. First work with my new supervisor @kordinglab, my old supervisor @meenakshik93 and the inimitable @sudh8887. Was great fun to look at the basis of the standard approaches we all use. (7/7).
1
0
8
Work by @nacloos Christopher Cueva and @GuangyuRobert on alignment scores relation to behaviors and work by Yeena Han and @thisismyhat about system identification within networks only works with some measures. (6/7).
1
0
8
Also check work by @ermgrant and @SaxeLab on how the choice of comparison technique should be guided by the specific use case, @bkhmsi @ABosselut and @martin_schrimpf with similar results for language (5/7).
1
0
10