Zobrazeno 1 - 10
of 40
pro vyhledávání: '"Klindt, David A."'
Autor:
O'Neill, Charles, Klindt, David
A recent line of work has shown promise in using sparse autoencoders (SAEs) to uncover interpretable features in neural network representations. However, the simple linear-nonlinear encoding mechanism in SAEs limits their ability to perform accurate
Externí odkaz:
http://arxiv.org/abs/2411.13117
Autor:
Reizinger, Patrik, Bizeul, Alice, Juhos, Attila, Vogt, Julia E., Balestriero, Randall, Brendel, Wieland, Klindt, David
Supervised learning has become a cornerstone of modern machine learning, yet a comprehensive theory explaining its effectiveness remains elusive. Empirical phenomena, such as neural analogy-making and the linear representation hypothesis, suggest tha
Externí odkaz:
http://arxiv.org/abs/2410.21869
Deep Learning is often depicted as a trio of data-architecture-loss. Yet, recent Self Supervised Learning (SSL) solutions have introduced numerous additional design choices, e.g., a projector network, positive views, or teacher-student networks. Thes
Externí odkaz:
http://arxiv.org/abs/2406.10743
Get rich quick: exact solutions reveal how unbalanced initializations promote rapid feature learning
Autor:
Kunin, Daniel, Raventós, Allan, Dominé, Clémentine, Chen, Feng, Klindt, David, Saxe, Andrew, Ganguli, Surya
While the impressive performance of modern neural networks is often attributed to their capacity to efficiently extract task-relevant features from data, the mechanisms underlying this rich feature learning regime remain elusive, with much of our the
Externí odkaz:
http://arxiv.org/abs/2406.06158
Single neurons in neural networks are often interpretable in that they represent individual, intuitively meaningful features. However, many neurons exhibit $\textit{mixed selectivity}$, i.e., they represent multiple unrelated features. A recent hypot
Externí odkaz:
http://arxiv.org/abs/2310.11431
Autor:
Bjerke, Martin, Schott, Lukas, Jensen, Kristopher T., Battistin, Claudia, Klindt, David A., Dunn, Benjamin A.
Systems neuroscience relies on two complementary views of neural data, characterized by single neuron tuning curves and analysis of population activity. These two perspectives combine elegantly in neural latent variable models that constrain the rela
Externí odkaz:
http://arxiv.org/abs/2210.03155
Autor:
Myers, Adele, Utpala, Saiteja, Talbar, Shubham, Sanborn, Sophia, Shewmake, Christian, Donnat, Claire, Mathe, Johan, Lupo, Umberto, Sonthalia, Rishi, Cui, Xinyue, Szwagier, Tom, Pignet, Arthur, Bergsson, Andri, Hauberg, Soren, Nielsen, Dmitriy, Sommer, Stefan, Klindt, David, Hermansen, Erik, Vaupel, Melvin, Dunn, Benjamin, Xiong, Jeffrey, Aharony, Noga, Pe'er, Itsik, Ambellan, Felix, Hanik, Martin, Nava-Yazdani, Esfandiar, von Tycowicz, Christoph, Miolane, Nina
This paper presents the computational challenge on differential geometry and topology that was hosted within the ICLR 2022 workshop ``Geometric and Topological Representation Learning". The competition asked participants to provide implementations of
Externí odkaz:
http://arxiv.org/abs/2206.09048
The tremendous success of generative models in recent years raises the question whether they can also be used to perform classification. Generative models have been used as adversarially robust classifiers on simple datasets such as MNIST, but this r
Externí odkaz:
http://arxiv.org/abs/2110.00473
Autor:
Klindt, David, Schott, Lukas, Sharma, Yash, Ustyuzhaninov, Ivan, Brendel, Wieland, Bethge, Matthias, Paiton, Dylan
We construct an unsupervised learning model that achieves nonlinear disentanglement of underlying factors of variation in naturalistic videos. Previous work suggests that representations can be disentangled if all but a few factors in the environment
Externí odkaz:
http://arxiv.org/abs/2007.10930
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.