PouyaBashivan Profile Banner
pouya bashivan Profile
pouya bashivan

@PouyaBashivan

Followers
997
Following
1K
Media
39
Statuses
320

Proud husband & dad | Assistant Prof @McGillPhysioloG | member @IPNMcGill @MILAMontreal | studying deep artificial/biological neural nets

Montreal, QC
Joined October 2012
Don't wanna be here? Send us removal request.
@PouyaBashivan
pouya bashivan
7 months
How do RNNs encode and maintain high dimensional visual information to perform memory-dependent tasks? .Checkout the new paper led by PhD student @xiaoxuan_lei (NeurIPS2024) with @taku_ito1.
@xiaoxuan_lei
xiaoxuan_Lei
7 months
🌟 New Research Alert! 🌟.Excited to share our latest work (accepted to NeurIPS2024) on understanding working memory in multi-task RNN models using naturalistic stimuli!: with @taku_ito1 and @PouyaBashivan .#tweeprint below:
Tweet media one
1
5
41
@PouyaBashivan
pouya bashivan
9 days
RT @fenildoshi009: 🧵 What if two images have the same local parts but represent different global shapes purely through part arrangement? Hu….
0
110
0
@PouyaBashivan
pouya bashivan
9 days
Come up north!.
@roydanroy
Dan Roy
9 days
Would love help identifying amazing ML researchers with strong connections to Canada who are currently outside Canada (thus potentially targets for recruitment as US situation deteriorates). DMs please. Retweet please.
0
0
1
@PouyaBashivan
pouya bashivan
15 days
🚨New paper 🚨.World models bake knowledge into weights, making them slow to adapt when environments change. We built one that infers from episodic memories instead. Check it out if you are interested in world modeling, episodic memory, spatial reasoning, or all of the above.
@HeHerbie
Herbie He
15 days
🧠 Can a neural network build a spatial map from scattered episodic experiences like humans do?. We introduce the Episodic Spatial World Model (ESWM)—a model that constructs flexible internal world models from sparse, disjoint memories. 🧵👇 [1/12]
Tweet media one
0
6
25
@PouyaBashivan
pouya bashivan
2 months
RT @dyamins: Come to our CCN workshop! Blending iophysical constraints and neural networks. Topographical ANNs + and much more. @meen….
0
9
0
@PouyaBashivan
pouya bashivan
3 months
Come by @great_caster poster if you are at #ICLR2025 and interested in topographical neural networks! .Whenđź“…: Friday, April 25 from 10:00 AM to 12:30 PM Where: Hall 3 + Hall 2B #60.
@great_caster
Amir Ozhan Dehghani
3 months
I’ll be at @iclr_conf presenting our work “Credit-based self organizing maps: training deep topographic networks with minimal performance degradation” — if you're into #NeuroAI, cortical topography, vision, or just up for a good convo, drop by and DM me! 🧠✨
Tweet media one
0
4
19
@PouyaBashivan
pouya bashivan
4 months
At #COSYNE2025 ? Come by @MotaharehPR 's poster at 1pm [2-089] if you like to know about how cool her NN model of visual search is! Trained de novo on visual search, its fast, efficient, mimics human behaviour, and has a beautiful neural geometry.
Tweet media one
0
2
36
@PouyaBashivan
pouya bashivan
4 months
RT @pcastr: Looking to hire a student researcher to work on cool project for 6 months in DeepMind Montreal. Reqs: .- Full-time masters/Ph….
0
56
0
@PouyaBashivan
pouya bashivan
4 months
RT @roydanroy: Very troubling. I believe the U.S. has just ruled itself out as a reasonable destination for scientific conferences. @NeurI….
0
20
0
@PouyaBashivan
pouya bashivan
4 months
Check out our latest work (and the tweeprint), Credit-based SOMs for training topographical deep nets! Very proud of this work led by the first undergraduate in my lab! Great job @great_caster.
@great_caster
Amir Ozhan Dehghani
4 months
I am excited to share that my undergraduate research has now been accepted to #ICLR2025. 📎: 🧑‍💻: Tweeprint🧵⬇️
Tweet media one
0
4
17
@PouyaBashivan
pouya bashivan
7 months
If you’re at NeurIPS, Check out @xiaoxuan_lei poster on representational geometry in RNN models of working memory using natural sensory inputs!.
@xiaoxuan_lei
xiaoxuan_Lei
7 months
📌 Poster Session:.⏰ When: TODAY, Thu, Dec 12, 4:30 p.m. – 7:30 p.m. PST.📍 Where: East Exhibit Hall A-C, #3705.📄 What: Geometry of Naturalistic Object Representations in Recurrent Neural Network Models of Working Memory. Hope to see you there! @PouyaBashivan @taku_ito1.
0
2
3
@PouyaBashivan
pouya bashivan
8 months
RT @ShahabBakht: This is a great opportunity to secure funding for postdoc. My lab has a few research directions that align with the IVAD….
0
7
0
@PouyaBashivan
pouya bashivan
9 months
RT @jpineau1: Interesting analysis on the impact of open LLMs.
0
5
0
@PouyaBashivan
pouya bashivan
9 months
4/ simulating neural activity with linear mapping methods are important tools for both our scientific understanding and pushing towards potential applications like neural control.
0
0
4
@PouyaBashivan
pouya bashivan
9 months
3/ linear regression is not the only way for finding linear maps. Constrained domain specific approaches like those from @bethgelab and @AToliasLab @sinzlab generalize much better and should be more widely used/studied.
1
0
3
@PouyaBashivan
pouya bashivan
9 months
2/ but often the observed overfitting is due to lack of sample diversity and larger datasets like @KendrickKay NSD and continuously growing BrainScore are important steps towards more reliable ranking for models with these methods.
1
0
3
@PouyaBashivan
pouya bashivan
9 months
1/ I agree that linear regression is not a silver bullet. We already know that simple regression-based maps don’t generalize well to OOD.
1
0
5
@PouyaBashivan
pouya bashivan
9 months
I have been following the discussions around new work from @RylanSchaeffer et al. in the past few days including very thoughtful responses by @aran_nayebi @AndrewLampinen that pointed out several misconceptions. A few points worth adding:.
@RylanSchaeffer
Rylan Schaeffer
9 months
My 2nd to last #neuroscience paper will appear @unireps !!. đź§ đź§  Maximizing Neural Regression Scores May Not Identify Good Models of the Brain đź§ đź§ . w/ @KhonaMikail @neurostrow @BrandoHablando @sanmikoyejo . Answering a puzzle 2 years in the making. 1/12.
1
5
28
@PouyaBashivan
pouya bashivan
9 months
RT @Mila_Quebec: Mila's annual supervision request process opens on October 15 to receive MSc and PhD applications for Fall 2025 admission!….
0
80
0
@PouyaBashivan
pouya bashivan
9 months
RT @ShahabBakht: I’ll be recruiting 1-2 graduate students for Fall 2025 to work on visual learning generalization in humans and artificial….
0
91
0