Stanford NeuroAI Lab

159 posts

Stanford NeuroAI Lab

Stanford NeuroAI Lab

@NeuroAILab

Neuroscience, artificial intelligence, and psychology research at Stanford University (PI: Dan Yamins)

Stanford, CA Katılım Kasım 2017
118 Takip Edilen3K Takipçiler
Stanford NeuroAI Lab retweetledi
Aran Nayebi
Aran Nayebi@aran_nayebi·
Excited to share our work on Mouse Visual Cortex is now published in @ploscompbiol: journals.plos.org/ploscompbiol/a… #ploscompbiolauthor We also release our SOTA pretrained models & our Pytorch library of SSL methods so others can build their own models easily: github.com/neuroailab/mou…
Aran Nayebi@aran_nayebi

1/8 Can we use embodied AI to gain insight into *why* neural systems are as they are? In previous work👇, we demonstrated that a contrastive unsupervised objective substantially outperforms supervised object categorization at generating networks that predict mouse visual cortex.

English
1
12
50
12.2K
Stanford NeuroAI Lab retweetledi
Aran Nayebi
Aran Nayebi@aran_nayebi·
If you're attending #cosyne2023, stop by our Poster III-002 👇 this Saturday at 8:30 pm on "Mouse visual cortex as a limited resource system that self-learns an ecologically-general representation"! w/ @NathanKong @ChengxuZhuang Justin Gardner @amnorcia @dyamins
Aran Nayebi tweet media
English
1
7
26
4.2K
Stanford NeuroAI Lab retweetledi
Aran Nayebi
Aran Nayebi@aran_nayebi·
11/15 Finally, the discussion of hyperparameters has come up most recently in the context of MEC models. Actually, one main result in our NeurIPS '21 paper was that pure path integration alone was *not* sufficient to match responses in MEC. (Figs 2 & 3 in biorxiv.org/content/10.110…)
English
2
1
1
0
Stanford NeuroAI Lab retweetledi
Aran Nayebi
Aran Nayebi@aran_nayebi·
9/15 Alongside theoretical considerations, an empirical criterion for picking a (model, metric) pair could be if it enables better neural population control, compared to alternatives. A good scientific theory should help control the phenomena it seeks to explain.
English
1
1
0
0
Stanford NeuroAI Lab retweetledi
Aran Nayebi
Aran Nayebi@aran_nayebi·
1/15 This is an important point worth underscoring. As I’ll elaborate here below -- there is actually a lot of shared perspective between critiques of NeuroAI with the main considerations of those who practice it. It also leads to some new directions that I'll note!🧵👇
Blake Richards@tyrell_turing

@jmourabarbosa @martin_schrimpf @TimKietzmann @JamesJDiCarlo @dyamins @NKriegeskorte @neurograce I'm afraid I must bust out my go-to reaction. 😉 The utility of the 3 papers here, as with other similar ones, is to show what our current models are not correctly capturing. But, they do not demonstrate that multi-layer ANNs are the wrong tool for modelling the brain.

English
1
10
38
0
Stanford NeuroAI Lab retweetledi
Aran Nayebi
Aran Nayebi@aran_nayebi·
8/8 We think answering these Why questions is one of most productive uses for task-driven deep neural networks in neuroscience. More details found here: biorxiv.org/content/10.110…
English
2
2
20
0
Stanford NeuroAI Lab retweetledi
Aran Nayebi
Aran Nayebi@aran_nayebi·
1/8 Can we use embodied AI to gain insight into *why* neural systems are as they are? In previous work👇, we demonstrated that a contrastive unsupervised objective substantially outperforms supervised object categorization at generating networks that predict mouse visual cortex.
Aran Nayebi@aran_nayebi

Here we develop "Unsupervised Models of Mouse Visual Cortex" Co-lead with @NathanKong w/ @ChengxuZhuang, Justin Gardner, @amnorcia, @dyamins #tweetprint below 👇

English
4
61
346
0
Stanford NeuroAI Lab retweetledi
Aran Nayebi
Aran Nayebi@aran_nayebi·
1/3 We release our ImageNet pretrained Recurrent CNN models, which currently best explain neural dynamics & temporally varying visual behaviors. Ready to be used with 1 line of code! Models: tinyurl.com/ms88azrv Paper (to appear in Neural Computation): tinyurl.com/2p8kcka7
Aran Nayebi@aran_nayebi

Glad to share a preprint of our work on "Goal-Driven Recurrent Neural Network Models of the Ventral Visual Stream"! w/ the "ConvRNN Crew" @jvrsgsty @recursus @KohitijKar @qbilius @SuryaGanguli @SussilloDavid @JamesJDiCarlo @dyamins #tweetprint below👇

English
1
66
265
0
Stanford NeuroAI Lab retweetledi
Aran Nayebi
Aran Nayebi@aran_nayebi·
1/ Interested in how task-driven neural networks help us understand the diverse cell types in medial entorhinal cortex (MEC), a brain area that plays a key role in navigation & memory? Stop by #NeurIPS2021 poster session 6 tomorrow (8:30 am PT, Spot F0)! tinyurl.com/4vkwzj86
Aran Nayebi tweet media
English
1
11
53
0
Stanford NeuroAI Lab retweetledi
Daniel Bear
Daniel Bear@recursus·
Do AI models understand everyday physical phenomena like we do, or are they missing key elements of human judgment? Check out #Physion, our #NeurIPS2021 benchmark for comparing physical prediction in models and humans, to find out! Paper, Dataset, Talk: bit.ly/3Evq3r5
Daniel Bear@recursus

How well do today's AI models understand the physical structure and dynamics of visual scenes? Introducing #Physion: a dataset/benchmark featuring objects that roll, slide, fall, fold, collide, connect, contain, and more! preprint: arxiv.org/abs/2106.08261

English
1
14
51
0
Stanford NeuroAI Lab retweetledi
Martin Schrimpf
Martin Schrimpf@martin_schrimpf·
Computational neuroscience has lately had great success at modeling perception with ANNs - but it has been unclear if this approach translates to higher cognitive systems. We made some exciting progress in modeling human language processing biorxiv.org/content/10.110… #tweeprint 1/
Martin Schrimpf tweet media
English
3
137
500
0
Stanford NeuroAI Lab retweetledi
Aran Nayebi
Aran Nayebi@aran_nayebi·
1/ People study medial entorhinal cortex (MEC) because of its key role in navigation and memory. In our new paper we build neural network models that explain the full diversity of neural responses in MEC. To appear as a #NeurIPS2021 Spotlight! Tweetprint below 👇🧠
bioRxiv Neuroscience@biorxiv_neursci

Explaining heterogeneity in medial entorhinal cortex with task-driven neural networks biorxiv.org/cgi/content/sh… #biorxiv_neursci

English
3
32
117
0
Stanford NeuroAI Lab retweetledi
Matthias Niessner
Matthias Niessner@MattNiessner·
(1/n) How to start a deep learning project? We use a remarkably streamlined step-by-step process to set up deep learning projects. At the same time, people who are new to deep learning tend to always make the same (avoidable) mistakes. Check out the thread below! 🧵
English
30
597
2.8K
0
Stanford NeuroAI Lab retweetledi
Fei-Fei Li
Fei-Fei Li@drfeifei·
Large-language models like #GPT3 have shown tsunami impact in #AI world. We predict profound impact of these models in countless applications to come. 100+ researchers @StanfordHAI have released a paper abt the present &future of these Foundation Models. arxiv.org/pdf/2108.07258…
English
10
147
518
0
Stanford NeuroAI Lab retweetledi
William Shen
William Shen@shenbokui·
[1/2] Excited to share that iGibson 1.0 is accepted to #IROS2021 🤖 Cool features and scenes to develop and train robots for interactive tasks in large virtual environments: website: svl.stanford.edu/igibson/ Arxiv: arxiv.org/abs/2012.02924 Code: 👉 pip install "igibson==1.0.*" 👈
GIF
English
2
19
68
0

Keşfet

@PLOSCompBiol @CosyneMeeting @jvrsgsty @aran_nayebi @luosha @dyamins @NathanKong @ChengxuZhuang