Zobrazeno 1 - 10
of 927
pro vyhledávání: '"Yevick A"'
Autor:
Salah, Ahmed, Yevick, David
This paper demonstrates that grokking behavior in modular arithmetic with a modulus P in a neural network can be controlled by modifying the profile of the activation function as well as the depth and width of the model. Plotting the even PCA project
Externí odkaz:
http://arxiv.org/abs/2411.05353
Autor:
Yevick, David
A simply implemented activation function with even cubic nonlinearity is introduced that increases the accuracy of neural networks without substantial additional computational resources. This is partially enabled through an apparent tradeoff between
Externí odkaz:
http://arxiv.org/abs/2403.19896
Autor:
Salah, Ahmed, Yevick, David
This paper introduces a modified variational autoencoder (VAEs) that contains an additional neural network branch. The resulting branched VAE (BVAE) contributes a classification component based on the class labels to the total loss and therefore impa
Externí odkaz:
http://arxiv.org/abs/2401.02526
Autor:
Yevick, David, Hutchison, Karolina
This paper examines the relationship between the behavior of a neural network and the distribution formed from the projections of the data records into the space spanned by the low-order principal components of the training data. For example, in a be
Externí odkaz:
http://arxiv.org/abs/2312.01392
Autor:
Yevick, David
This paper demonstrates that a simple modification of the variational autoencoder (VAE) formalism enables the method to identify and classify rotated and distorted digits. In particular, the conventional objective (cost) function employed during the
Externí odkaz:
http://arxiv.org/abs/2206.13388
Autor:
Salman Alam, Bibi Najma, Abhinav Singh, Jeremy Laprade, Gauri Gajeshwar, Hannah G. Yevick, Aparna Baskaran, Peter J. Foster, Guillaume Duclos
Publikováno v:
Physical Review X, Vol 14, Iss 4, p 041002 (2024)
Active nematic liquid crystals have the remarkable ability to spontaneously deform and flow in the absence of any external driving force. While living materials with orientational order, such as the mitotic spindle, can self-assemble in quiescent act
Externí odkaz:
https://doaj.org/article/fd97f6c230344981bea85f0aba117aa8
Deep learning has transformed the way large and complex image datasets can be processed, reshaping what is possible in bioimage analysis. As the complexity and size of bioimage data continues to grow, this new analysis paradigm is becoming increasing
Externí odkaz:
http://arxiv.org/abs/2107.02584
Autor:
Yevick, David
Variational autoencoders employ an encoding neural network to generate a probabilistic representation of a data set within a low-dimensional space of latent variables followed by a decoding stage that maps the latent variables back to the original va
Externí odkaz:
http://arxiv.org/abs/2104.06368
Autor:
Yevick, David
This paper examines several applications of principal component analysis (PCA) to physical systems. The first of these demonstrates that the principal components in a basis of appropriate system variables can be employed to identify physically conser
Externí odkaz:
http://arxiv.org/abs/2005.01613
Autor:
Yevick, David, Melko, Roger
Restricted Boltzmann machine (RBM) provide a general framework for modeling physical systems, but their behavior is dependent on hyperparameters such as the learning rate, the number of hidden nodes and the form of the threshold function. This articl
Externí odkaz:
http://arxiv.org/abs/2004.12867