Zobrazeno 1 - 10
of 178
pro vyhledávání: '"Golubeva, Anna"'
Dynamic Sparse Training (DST) methods achieve state-of-the-art results in sparse neural network training, matching the generalization of dense models while enabling sparse training and inference. Although the resulting models are highly sparse and th
Externí odkaz:
http://arxiv.org/abs/2305.02299
Autor:
Galloway, Angus, Golubeva, Anna, Salem, Mahmoud, Nica, Mihai, Ioannou, Yani, Taylor, Graham W.
Estimating the Generalization Error (GE) of Deep Neural Networks (DNNs) is an important task that often relies on availability of held-out data. The ability to better predict GE based on a single training set may yield overarching DNN design principl
Externí odkaz:
http://arxiv.org/abs/2207.09408
Autor:
Golubeva, Anna, Melko, Roger G.
Restricted Boltzmann machines (RBMs) have proven to be a powerful tool for learning quantum wavefunction representations from qubit projective measurement data. Since the number of classical parameters needed to encode a quantum wavefunction scales r
Externí odkaz:
http://arxiv.org/abs/2110.03676
Empirical studies demonstrate that the performance of neural networks improves with increasing number of parameters. In most of these studies, the number of parameters is increased by increasing the network width. This begs the question: Is the obser
Externí odkaz:
http://arxiv.org/abs/2010.14495
Autor:
Sehayek, Dan, Golubeva, Anna, Albergo, Michael S., Kulchytskyy, Bohdan, Torlai, Giacomo, Melko, Roger G.
Publikováno v:
Phys. Rev. B 100, 195125 (2019)
Generative modeling with machine learning has provided a new perspective on the data-driven task of reconstructing quantum states from a set of qubit measurements. As increasingly large experimental quantum devices are built in laboratories, the ques
Externí odkaz:
http://arxiv.org/abs/1908.07532
Batch normalization (batch norm) is often used in an attempt to stabilize and accelerate training in deep neural networks. In many cases it indeed decreases the number of parameter updates required to achieve low training error. However, it also redu
Externí odkaz:
http://arxiv.org/abs/1905.02161
Autor:
Beach, Matthew J. S., De Vlugt, Isaac, Golubeva, Anna, Huembeli, Patrick, Kulchytskyy, Bohdan, Luo, Xiuzhe, Melko, Roger G., Merali, Ejaaz, Torlai, Giacomo
Publikováno v:
SciPost Phys. 7, 009 (2019)
As we enter a new era of quantum technology, it is increasingly important to develop methods to aid in the accurate preparation of quantum states for a variety of materials, matter, and devices. Computational techniques can be used to reconstruct a s
Externí odkaz:
http://arxiv.org/abs/1812.09329
We analyze the adversarial examples problem in terms of a model's fault tolerance with respect to its input. Whereas previous work focuses on arbitrarily strict threat models, i.e., $\epsilon$-perturbations, we consider arbitrary valid inputs and pro
Externí odkaz:
http://arxiv.org/abs/1811.12601
Autor:
Sen, Paromita, Sherwin, Eoin, Sandhu, Kiran, Bastiaanssen, Thomaz F.S., Moloney, Gerard M., Golubeva, Anna, Fitzgerald, Patrick, Paula Ventura Da Silva, Ana, Chruścicka-Smaga, Barbara, Olavarría-Ramírez, Loreto, Druelle, Clementine, Campos, David, Jayaprakash, Pooja, Rea, Kieran, Jeffery, Ian B., Savignac, Helene, Chetal, Sasha, Mulder, Imke, Schellekens, Harriet, Dinan, Timothy G., Cryan, John F.
Publikováno v:
In Brain Behavior and Immunity November 2022 106:115-126
Autor:
Collins, James M., Caputi, Valentina, Manurung, Sarmauli, Gross, Gabriele, Fitzgerald, Patrick, Golubeva, Anna V., Popov, Jelena, Deady, Clara, Dinan, Timothy G., Cryan, John F., O'Mahony, Siobhain M.
Publikováno v:
In Neuropharmacology 1 June 2022 210