Zobrazeno 1 - 10
of 5 255
pro vyhledávání: '"Clerico A"'
Traditional generalization results in statistical learning require a training data set made of independently drawn examples. Most of the recent efforts to relax this independence assumption have considered either purely temporal (mixing) dependencies
Externí odkaz:
http://arxiv.org/abs/2410.08977
Autor:
Clerico, Victoria, Snyder, Shay, Lohia, Arya, Kaiser, Md Abdullah-Al, Schwartz, Gregory, Jaiswal, Akhilesh, Parsa, Maryam
Dynamic Vision Sensors (DVS) have emerged as a revolutionary technology with a high temporal resolution that far surpasses RGB cameras. DVS technology draws biological inspiration from photoreceptors and the initial retinal synapse. Our research show
Externí odkaz:
http://arxiv.org/abs/2408.09454
Autor:
Sinaga, Jason, Clerico, Victoria, Kaiser, Md Abdullah-Al, Snyder, Shay, Lohia, Arya, Schwartz, Gregory, Parsa, Maryam, Jaiswal, Akhilesh
Recent advances in retinal neuroscience have fueled various hardware and algorithmic efforts to develop retina-inspired solutions for computer vision tasks. In this work, we focus on a fundamental visual feature within the mammalian retina, Object Mo
Externí odkaz:
http://arxiv.org/abs/2408.08320
Autor:
Estrada-Álvarez, Jorge, Salvador-Sánchez, Juan, Pérez-Rodríguez, Ana, Sánchez-Sánchez, Carlos, Clericò, Vito, Vaquero, Daniel, Watanabe, Kenji, Taniguchi, Takashi, Diez, Enrique, Domínguez-Adame, Francisco, Amado, Mario, Díaz, Elena
Viscous electron flow exhibits exotic signatures such as superballistic conduction. Bending the geometry of the device is a must to observe hydrodynamic effects. To this end, we build three antidot graphene superlattices with different hole diameters
Externí odkaz:
http://arxiv.org/abs/2407.04527
We study the generalization error of statistical learning algorithms in a non-i.i.d. setting, where the training data is sampled from a stationary mixing process. We develop an analytic framework for this scenario based on a reduction to online learn
Externí odkaz:
http://arxiv.org/abs/2406.12600
In parallel with the continuously increasing parameter space dimensionality, search and optimization algorithms should support distributed parameter evaluations to reduce cumulative runtime. Intel's neuromorphic optimization library, Lava-Optimizatio
Externí odkaz:
http://arxiv.org/abs/2405.04387
Autor:
Snyder, Shay, Clerico, Victoria, Cong, Guojing, Kulkarni, Shruti, Schuman, Catherine, Risbud, Sumedh R., Parsa, Maryam
Graph neural networks have emerged as a specialized branch of deep learning, designed to address problems where pairwise relations between objects are crucial. Recent advancements utilize graph convolutional neural networks to extract features within
Externí odkaz:
http://arxiv.org/abs/2404.17048
Autor:
Clerico, Eugenio, Guedj, Benjamin
We establish explicit dynamics for neural networks whose training objective has a regularising term that constrains the parameters to remain close to their initial value. This keeps the network in a lazy training regime, where the dynamics can be lin
Externí odkaz:
http://arxiv.org/abs/2312.13259
Although radar and communications signal classification are usually treated separately, they share similar characteristics, and methods applied in one domain can be potentially applied in the other. We propose a simple and unified scheme for the clas
Externí odkaz:
http://arxiv.org/abs/2305.03192
Autor:
Michele Clerico, Simone Ferrero, Beatrice Alessandria, Gian Maria Zaccaria, Elisa Genuardi, Simone Ragaini, Rita Tavarozzi, Federica Cavallo, Stefan Hohaus, Gerardo Musuraca, Angelo Michele Carella, Caterina Stelitano, Monica Tani, Gianluca Gaidano, Jacopo Olivieri, Sara Veronica Usai, Sara Galimberti, Francesca Re, Michael Mian, Claudia Castellino, Vincenzo Pavone, Andrea Evangelista, Benedetto Bruno, Sergio Cortelazzo, Roberto Passera, Marco Ladetto
Publikováno v:
Scientific Reports, Vol 14, Iss 1, Pp 1-9 (2024)
Abstract In the frontline high-dose phase 3 FIL-MCL0208 trial (NCT02354313), 8% of enrolled mantle cell lymphoma (MCL) patients could not be randomised to receive lenalidomide (LEN) maintenance vs observation after autologous stem cell transplantatio
Externí odkaz:
https://doaj.org/article/0fb90bbb8fcd4300b5901399a273825b