Zobrazeno 1 - 10
of 327
pro vyhledávání: '"Yevick, David"'
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:
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