Výsledky vyhledávání - "Maruan Al-Shedivat"

Progressive Generation of Long Text with Pretrained Language Models

Autor: Eric P. Xing, Maruan Al-Shedivat, Zichao Yang, Zhiting Hu, Bowen Tan

Publikováno v: NAACL-HLT

Large-scale language models (LMs) pretrained on massive corpora of text, such as GPT-2, are powerful open-domain text generators. However, as our systematic examination reveals, it is still challenging for such models to generate coherent long passag

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d4640f88900ed705597a2772dcee8284
https://doi.org/10.18653/v1/2021.naacl-main.341

Zobrazit plný text záznamu

Discriminative Subtyping of Lung Cancers from Histopathology Images via Contextual Deep Learning

Autor: Benjamin J. Lengerich, Sami Labbaki, Maruan Al-Shedivat, Jennifer Williams, Amir H. Alavi, Eric P. Xing

Summarizing multiple data modalities into a parsimonious cancer “subtype” is difficult because the most informative representation of each patient’s disease is not observed. We propose to model these latent summaries asdiscriminative subtypes:

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::eeec042e21cde3397c0b42a06cc19de9

Zobrazit plný text záznamu

Consistency by Agreement in Zero-shot Neural Machine Translation

Autor: Maruan Al-Shedivat, Ankur P. Parikh

Publikováno v: NAACL-HLT (1)

Generalization and reliability of multilingual translation often highly depend on the amount of available parallel data for each language pair of interest. In this paper, we focus on zero-shot generalization---a challenging setup that tests models on

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f2aceef803909a1c7ed4e56ef5f39d6f
http://arxiv.org/abs/1904.02338

Zobrazit plný text záznamu

Memristors Empower Spiking Neurons With Stochasticity

Autor: Rawan Naous, Maruan Al-Shedivat, Khaled N. Salama, Gert Cauwenberghs

Publikováno v: IEEE Journal on Emerging and Selected Topics in Circuits and Systems. 5:242-253

Recent theoretical studies have shown that probabilistic spiking can be interpreted as learning and inference in cortical microcircuits. This interpretation creates new opportunities for building neuromorphic systems driven by probabilistic learning

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::844199de476b6dc6e803a2aff6a20fc4
https://doi.org/10.1109/jetcas.2015.2435512

Zobrazit plný text záznamu

Stochastic synaptic plasticity with memristor crossbar arrays

Autor: Gert Cauwenberghs, Emre Neftci, Maruan Al-Shedivat, Rawan Naous, Khaled N. Salama

Publikováno v: ISCAS

Memristive devices have been shown to exhibit slow and stochastic resistive switching behavior under low-voltage, low-current operating conditions. Here we explore such mechanisms to emulate stochastic plasticity in memristor crossbar synapse arrays.

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::c9fbbe90665dc71622c7eef85d1d1426
https://doi.org/10.1109/iscas.2016.7538988

Zobrazit plný text záznamu

Stochastic Synapses Enable Efficient Brain-Inspired Learning Machines

Autor: Gert Cauwenberghs, Siddharth Joshi, Maruan Al-Shedivat, Bruno U. Pedroni, Emre Neftci

Publikováno v: Neftci, EO; Pedroni, BU; Joshi, S; Al-Shedivat, M; & Cauwenberghs, G. (2016). Stochastic synapses enable efficient brain-inspired learning machines. Frontiers in Neuroscience, 10(JUN). doi: 10.3389/fnins.2016.00241. UC Irvine: Retrieved from: http://www.escholarship.org/uc/item/62t6f9rs
Neftci, EO; Pedroni, BU; Joshi, S; Al-Shedivat, M; & Cauwenberghs, G. (2016). Stochastic Synapses Enable Efficient Brain-Inspired Learning Machines. FRONTIERS IN NEUROSCIENCE, 10. doi: 10.3389/fnins.2016.00241. UC Irvine: Retrieved from: http://www.escholarship.org/uc/item/4wf3185b
Frontiers in Neuroscience

© 2016 Neftci, Pedroni, Joshi, Al-Shedivat and Cauwenberghs. Recent studies have shown that synaptic unreliability is a robust and sufficient mechanism for inducing the stochasticity observed in cortex. Here, we introduce Synaptic Sampling Machines

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::72625eb8602ac7edc33228c294af4a80
https://escholarship.org/uc/item/4wf3185b

Zobrazit plný text záznamu

Inherently stochastic spiking neurons for probabilistic neural computation

Autor: Khaled N. Salama, Gert Cauwenberghs, Maruan Al-Shedivat, Emre Neftci, Rawan Naous

Publikováno v: NER

Neuromorphic engineering aims to design hardware that efficiently mimics neural circuitry and provides the means for emulating and studying neural systems. In this paper, we propose a new memristor-based neuron circuit that uniquely complements the s

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::c04afea3bd5e3bd88d0c3c0972857c41
https://doi.org/10.1109/ner.2015.7146633

Zobrazit plný text záznamu

Supervised Transfer Sparse Coding

Autor: Maruan Al-Shedivat, Wang, Jim Jing-Yan, Alzahrani, Majed, Huang, Jianhua Z., Xin Gao

Publikováno v: Scopus-Elsevier
KAUST Repository

A combination of the sparse coding and transfer learning techniques was shown to be accurate and robust in classification tasks where training and testing objects have a shared feature space but are sampled from different underlying distributions, i.

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e4d5bab3c805c7d4aacc0ade779fd79a
https://doi.org/10.1609/aaai.v28i1.8981

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání