Jonathan Karin
@jonathankarin.bsky.social
Reposted by Jonathan Karin
Jonathan Karin, Zoe Piran, Mor Nitzan: Enhancing Swarms Durability to Threats via Graph Signal Processing and GNN-based Generative Modeling https://arxiv.org/abs/2507.03039 https://arxiv.org/pdf/2507.03039 https://arxiv.org/html/2507.03039
July 8, 2025 at 6:51 AM
Jonathan Karin, Zoe Piran, Mor Nitzan: Enhancing Swarms Durability to Threats via Graph Signal Processing and GNN-based Generative Modeling https://arxiv.org/abs/2507.03039 https://arxiv.org/pdf/2507.03039 https://arxiv.org/html/2507.03039
Reposted by Jonathan Karin
Happy to share this- we analyze the hierarchical organization of attractor landscapes in dense associative memories and how it can facilitate transitions between attractor states. We use this to explain the control of transitions between stem and differentiated identities. arxiv.org/abs/2412.11336
Hierarchical Control of State Transitions in Dense Associative Memories
We analyze a generalization of Modern Hopfield networks that emerges naturally in the gene regulatory networks that control cellular identity. Here gene expression patterns correspond to stored memori...
arxiv.org
December 20, 2024 at 10:12 AM
Happy to share this- we analyze the hierarchical organization of attractor landscapes in dense associative memories and how it can facilitate transitions between attractor states. We use this to explain the control of transitions between stem and differentiated identities. arxiv.org/abs/2412.11336
1/3 Annotatability is out in Nature Computational Science! With Reshef Mintz,
@ravehlab.bsky.social
and @mornitzan.bsky.social
www.nature.com/articles/s43...
@ravehlab.bsky.social
and @mornitzan.bsky.social
www.nature.com/articles/s43...
Interpreting single-cell and spatial omics data using deep neural network training dynamics - Nature Computational Science
The Annotatability framework analyzes neural network training dynamics to interpret single-cell and spatial omics data. It identifies erroneous annotations and ambiguous cell states, infers trajectori...
www.nature.com
December 8, 2024 at 2:05 PM
1/3 Annotatability is out in Nature Computational Science! With Reshef Mintz,
@ravehlab.bsky.social
and @mornitzan.bsky.social
www.nature.com/articles/s43...
@ravehlab.bsky.social
and @mornitzan.bsky.social
www.nature.com/articles/s43...
1/3 Annotatability is out in Nature Computational Science! With Reshef Mintz,
@ravehlab.bsky.social and @mor_nitzan www.nature.com/articles/s43...
.
@ravehlab.bsky.social and @mor_nitzan www.nature.com/articles/s43...
.
Interpreting single-cell and spatial omics data using deep neural network training dynamics - Nature Computational Science
The Annotatability framework analyzes neural network training dynamics to interpret single-cell and spatial omics data. It identifies erroneous annotations and ambiguous cell states, infers trajectori...
www.nature.com
December 5, 2024 at 6:43 PM
1/3 Annotatability is out in Nature Computational Science! With Reshef Mintz,
@ravehlab.bsky.social and @mor_nitzan www.nature.com/articles/s43...
.
@ravehlab.bsky.social and @mor_nitzan www.nature.com/articles/s43...
.