Results 11 to 20 of about 1,246,962 (366)
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), 2021 We demonstrate that transformers obtain impressive performance even when some of the layers are randomly initialized and never updated. Inspired by old and well-established ideas in machine learning, we explore a variety of non-linear "reservoir" layers interspersed with regular transformer layers, and show improvements in wall-clock compute time until
Sheng Shen 0001 +5 more
openaire +2 more sources
Dynamic memristor-based reservoir computing for high-efficiency temporal signal processing
Nature Communications, 2021 Reservoir computing is a highly efficient network for processing temporal signals due to its low training cost compared to standard recurrent neural networks, and generating rich reservoir states is critical in the hardware implementation.
Yanan Zhong +5 more
semanticscholar +1 more source
The Investigation on Initiation and Propagation of Hydraulic Fractures in Shale Reservoir
Geofluids, 2021 Hydraulic fracturing is a necessary technique for shale gas exploitation. In order to have efficient stimulation treatment, a complex fracture network has to be developed, whereas with rich bedding planes and natural fractures, the mechanism of forming a
Xiangjun Liu +5 more
doaj +1 more source
All-ferroelectric implementation of reservoir computing
Nature Communications, 2023 Reservoir computing (RC) offers efficient temporal information processing with low training cost. All-ferroelectric implementation of RC is appealing because it can fully exploit the merits of ferroelectric memristors (e.g., good controllability ...
Zhiwei Chen +10 more
semanticscholar +1 more source
Petroleum Exploration and Development, 2020 : Taking the Cambrian Yuertus Formation outcrop profiles in the Aksu-Keping-Wushi areas of northwestern Tarim Basin as examples, the depositional environments of organic rich fine sediment were analyzed by examining the outcrop profiles macroscopically ...
Zhimin JIN +9 more
doaj +1 more source
In-sensor reservoir computing for language learning via two-dimensional memristors
Science Advances, 2021 High dimensionality and fading memory for in-sensor reservoir computing are achieved via two-dimensional memristors. The dynamic processing of optoelectronic signals carrying temporal and sequential information is critical to various machine learning ...
Linfeng Sun +9 more
semanticscholar +1 more source
Multifunctionality in a reservoir computer [PDF]
Chaos: An Interdisciplinary Journal of Nonlinear Science, 2021 Multifunctionality is a well observed phenomenological feature of biological neural networks and considered to be of fundamental importance to the survival of certain species over time. These multifunctional neural networks are capable of performing more than one task without changing any network connections.
Andrew Flynn +2 more
openaire +4 more sources
The Pattern of Vector Control in Malaria Endemic Areas of Central Java Province
BIO Web of Conferences, 2021 Malaria remains a public health problem in Indonesia, therefore, a study was conducted to guarantee a reduction in malaria cases and to support an elimination program.
Wigati R.A. +3 more
doaj +1 more source
Physical reservoir computing—an introductory perspective [PDF]
Japanese Journal of Applied Physics, 2020 Understanding the fundamental relationships between physics and its information-processing capability has been an active research topic for many years. Physical reservoir computing is a recently introduced framework that allows one to exploit the complex
K. Nakajima
semanticscholar +1 more source
Reservoir stack machines [PDF]
Neurocomputing, 2022 in print at the Journal ...
Paaßen, Benjamin +2 more
openaire +3 more sources