Zobrazeno 1 - 10
of 282
pro vyhledávání: '"Max Tegmark"'
Publikováno v:
Entropy, Vol 26, Iss 11, p 997 (2024)
How do transformers model physics? Do transformers model systems with interpretable analytical solutions or do they create an “alien physics” that is difficult for humans to decipher? We have taken a step towards demystifying this larger puzzle b
Externí odkaz:
https://doaj.org/article/de124c4a41a44e98ab0f236da00b2563
Publikováno v:
BMC Bioinformatics, Vol 23, Iss 1, Pp 1-18 (2022)
Abstract Background Determining cell identity in volumetric images of tagged neuronal nuclei is an ongoing challenge in contemporary neuroscience. Frequently, cell identity is determined by aligning and matching tags to an “atlas” of labeled neur
Externí odkaz:
https://doaj.org/article/7a6b49e33034454fbf8b3263055d6b8a
Publikováno v:
Entropy, Vol 26, Iss 1, p 41 (2023)
We introduce Brain-Inspired Modular Training (BIMT), a method for making neural networks more modular and interpretable. Inspired by brains, BIMT embeds neurons in a geometric space and augments the loss function with a cost proportional to the lengt
Externí odkaz:
https://doaj.org/article/2d52897fe9054cbdac32e40e03e5980d
Autor:
Maria Sundberg, Hannah Pinson, Richard S. Smith, Kellen D. Winden, Pooja Venugopal, Derek J. C. Tai, James F. Gusella, Michael E. Talkowski, Christopher A. Walsh, Max Tegmark, Mustafa Sahin
Publikováno v:
Nature Communications, Vol 12, Iss 1, Pp 1-20 (2021)
16p11.2 CNVs are associated with neurodevelopmental disorders. Here, the authors show that 16p11.2 deletion is associated with hyperactivation of human iPSC-derived dopaminergic neuron networks and is rescued by RHOA inhibition in vitro.
Externí odkaz:
https://doaj.org/article/b6ffb9fd39d845a3b76fce24f582a800
Autor:
Ricardo Vinuesa, Hossein Azizpour, Iolanda Leite, Madeline Balaam, Virginia Dignum, Sami Domisch, Anna Felländer, Simone Daniela Langhans, Max Tegmark, Francesco Fuso Nerini
Publikováno v:
Nature Communications, Vol 11, Iss 1, Pp 1-10 (2020)
Artificial intelligence (AI) is becoming more and more common in people’s lives. Here, the authors use an expert elicitation method to understand how AI may affect the achievement of the Sustainable Development Goals.
Externí odkaz:
https://doaj.org/article/63532085948b4fefa409fe7b270e7c06
Autor:
Samantha D'Alonzo, Max Tegmark
Publikováno v:
PLoS ONE, Vol 17, Iss 8, p e0271947 (2022)
We present an automated method for measuring media bias. Inferring which newspaper published a given article, based only on the frequencies with which it uses different phrases, leads to a conditional probability distribution whose analysis lets us a
Externí odkaz:
https://doaj.org/article/d5f8b500956b4a1092f8f284b7aaf54f
Publikováno v:
Entropy, Vol 25, Iss 1, p 175 (2023)
We explore unique considerations involved in fitting machine learning (ML) models to data with very high precision, as is often required for science applications. We empirically compare various function approximation methods and study how they scale
Externí odkaz:
https://doaj.org/article/dc4baa6bba6a4c96953418ad4a4a6725
Autor:
Shivam Gupta, Simone D. Langhans, Sami Domisch, Francesco Fuso-Nerini, Anna Felländer, Manuela Battaglini, Max Tegmark, Ricardo Vinuesa
Publikováno v:
Transportation Engineering, Vol 4, Iss , Pp 100064- (2021)
Since the early phase of the artificial-intelligence (AI) era expectations towards AI are high, with experts believing that AI paves the way for managing and handling various global challenges. However, the significant enabling and inhibiting influen
Externí odkaz:
https://doaj.org/article/ef389e94ad624e709346086fde718f0d
Publikováno v:
Entropy, Vol 24, Iss 6, p 771 (2022)
At the heart of both lossy compression and clustering is a trade-off between the fidelity and size of the learned representation. Our goal is to map out and study the Pareto frontier that quantifies this trade-off. We focus on the optimization of the
Externí odkaz:
https://doaj.org/article/d6d08c4552c04db3ac41992cd5200ac8
Publikováno v:
Entropy, Vol 21, Iss 10, p 924 (2019)
The Information Bottleneck (IB) method provides an insightful and principled approach for balancing compression and prediction for representation learning. The IB objective I ( X ; Z ) - β I ( Y ; Z ) employs a Lagrange multiplier β to tune this tr
Externí odkaz:
https://doaj.org/article/9b93e5151888417bb3bba3cd5ab8e20b