Zobrazeno 1 - 10
of 53
pro vyhledávání: '"Fabio Anselmi"'
Autor:
Josue O. Caro, Yilong Ju, Ryan Pyle, Sourav Dey, Wieland Brendel, Fabio Anselmi, Ankit B. Patel
Publikováno v:
Frontiers in Computational Neuroscience, Vol 18 (2024)
Adversarial attacks are still a significant challenge for neural networks. Recent efforts have shown that adversarial perturbations typically contain high-frequency features, but the root cause of this phenomenon remains unknown. Inspired by theoreti
Externí odkaz:
https://doaj.org/article/087906c1ef06470b8bf107bfe56c0b31
Autor:
Alice Antonello, Riccardo Bergamin, Nicola Calonaci, Jacob Househam, Salvatore Milite, Marc J. Williams, Fabio Anselmi, Alberto d’Onofrio, Vasavi Sundaram, Alona Sosinsky, William C. H. Cross, Giulio Caravagna
Publikováno v:
Genome Biology, Vol 25, Iss 1, Pp 1-40 (2024)
Abstract Copy number alterations (CNAs) are among the most important genetic events in cancer, but their detection from sequencing data is challenging because of unknown sample purity, tumor ploidy, and general intra-tumor heterogeneity. Here, we pre
Externí odkaz:
https://doaj.org/article/58afabce18a849ecb410852f49a33e9f
Autor:
Lucrezia Patruno, Salvatore Milite, Riccardo Bergamin, Nicola Calonaci, Alberto D'Onofrio, Fabio Anselmi, Marco Antoniotti, Alex Graudenzi, Giulio Caravagna
Publikováno v:
PLoS Computational Biology, Vol 19, Iss 11, p e1011557 (2023)
Single-cell RNA and ATAC sequencing technologies enable the examination of gene expression and chromatin accessibility in individual cells, providing insights into cellular phenotypes. In cancer research, it is important to consistently analyze these
Externí odkaz:
https://doaj.org/article/711143dbbcf84508bb43f4555ba5999a
Autor:
Fabio Anselmi, Luca Manzoni, Alberto D'onofrio, Alex Rodriguez, Giulio Caravagna, Luca Bortolussi, Francesca Cairoli
Publikováno v:
IEEE Access, Vol 11, Pp 47282-47290 (2023)
Symmetries in the data and how they constrain the learned weights of modern deep networks is still an open problem. In this work we study the simple case of fully connected shallow non-linear neural networks and consider two types of symmetries: full
Externí odkaz:
https://doaj.org/article/6ef8851554c34f7c87ec8206b6585ca6
Autor:
Zhe Li, Josue Ortega Caro, Evgenia Rusak, Wieland Brendel, Matthias Bethge, Fabio Anselmi, Ankit B Patel, Andreas S Tolias, Xaq Pitkow
Publikováno v:
PLoS Computational Biology, Vol 19, Iss 3, p e1010932 (2023)
Machine learning models have difficulty generalizing to data outside of the distribution they were trained on. In particular, vision models are usually vulnerable to adversarial attacks or common corruptions, to which the human visual system is robus
Externí odkaz:
https://doaj.org/article/3e136536bcab42e1b0ed458a6e49b9ad
Autor:
Fabio Anselmi, Tomaso Poggio
Publikováno v:
IEEE Access, Vol 10, Pp 102475-102491 (2022)
We review and apply a computational theory based on the hypothesis that the feedforward path of the ventral stream in visual cortex’s main function is the encoding of invariant representations of images. A key justification of the theory is provide
Externí odkaz:
https://doaj.org/article/3d98d68688624d91b92711927ad0935a
Autor:
Fabio Anselmi, Ankit B. Patel
Publikováno v:
Frontiers in Computational Neuroscience, Vol 16 (2022)
Externí odkaz:
https://doaj.org/article/480679df2a8b48c38c541d2ad7b513a1
Autor:
Nikos Karantzas, Emma Besier, Josue Ortega Caro, Xaq Pitkow, Andreas S. Tolias, Ankit B. Patel, Fabio Anselmi
Publikováno v:
Frontiers in Artificial Intelligence, Vol 5 (2022)
Despite the enormous success of artificial neural networks (ANNs) in many disciplines, the characterization of their computations and the origin of key properties such as generalization and robustness remain open questions. Recent literature suggests
Externí odkaz:
https://doaj.org/article/7ea7bb52abb44d12a7344e304625acda
Autor:
Justin Sahs, Ryan Pyle, Aneel Damaraju, Josue Ortega Caro, Onur Tavaslioglu, Andy Lu, Fabio Anselmi, Ankit B. Patel
Publikováno v:
Frontiers in Artificial Intelligence, Vol 5 (2022)
Understanding the learning dynamics and inductive bias of neural networks (NNs) is hindered by the opacity of the relationship between NN parameters and the function represented. Partially, this is due to symmetries inherent within the NN parameteriz
Externí odkaz:
https://doaj.org/article/e2330b9147f54188bde5e265df70a068
Publikováno v:
PLoS Computational Biology, Vol 11, Iss 10, p e1004390 (2015)
Is visual cortex made up of general-purpose information processing machinery, or does it consist of a collection of specialized modules? If prior knowledge, acquired from learning a set of objects is only transferable to new objects that share proper
Externí odkaz:
https://doaj.org/article/edccd7c5a94c41ebba35f8e26a997228