Results 81 to 90 of about 5,451,620 (296)

A lecture transcription system combining neural network acoustic and language models [PDF]

, 2013
This paper presents a new system for automatic transcription of lectures. The system combines a number of novel features, including deep neural network acoustic models using multi-level adaptive networks to incorporate out-of-domain information, and ...
Hori, C, Bell, P, Swietojanski, P, Wu, Y, Yamamoto, H, McInnes, F, Renals, S   +6 more
core  

Inhibition of MEKK3 Prevents Cerebral Cavernous Malformation Progression Via Restoring Endothelial Integrity and Restricting Microglial Activation

Advanced Science, EarlyView.
In this study, we demonstrate that aberrant MEKK3 signaling in endothelial cells and microglia drives the progression of cerebral cavernous malformations (CCMs). Furthermore, we identify DPDH as a potent small‐molecule MEKK3 inhibitor with substantial therapeutic potential for CCM treatment.
Weiwei Zheng, Suyun Yu, Liwenyu Chen, Jing Ma, Peiliang Shen, Chang Yu, Xiaoqing Xin, Qiuhong Shen, Jing Chen, Song Ke, Hao Liu, Xiaobing Jiang, Ruogu Qi, Juming Yan, Jia Li, Jaesung P. Choi, Yin Lu, Yang Zhao   +17 more
wiley   +1 more source

Hierarchical recurrent neural network for video summarization

, 2017
Exploiting the temporal dependency among video frames or subshots is very important for the task of video summarization. Practically, RNN is good at temporal dependency modeling, and has achieved overwhelming performance in many video-based tasks, such
Lu, Xiaoqiang, Xiaoqiang Lu, Li, Xuelong, Bin Zhao, Zhao, Bin, Xuelong Li   +5 more
core   +1 more source

Enhanced High Dimensionality and the Information Processing Capacity in Interfered Spin Wave‐Based Reservoir Computing, Achieved With Eight Detectors

Advanced Electronic Materials, EarlyView.
Physical reservoir computing (PRC) based on spin wave interference has demonstrated high computational performance, yet room for improvement remains. In this study, we fabricated this concept PRC with eight detectors and evaluated the impact of the number of detectors using a chaotic time series prediction task.
Sota Hikasa, Wataru Namiki, Daiki Nishioka, Maki Nishimura, Ryo Iguchi, Kazuya Terabe, Takashi Tsuchiya   +6 more
wiley   +1 more source

PNNARMA model: an alternative to phenomenological models in chemical reactors [PDF]

, 2001
This paper is focused on the development of non-linear neural models able to provide appropriate predictions when acting as process simulators. Parallel identification models can be used for this purpose.
J.M. Zaldı́var, Zaldívar, J.M., Galván, Inés M., I.M. Galván, P. Isasi, Isasi, Pedro   +5 more
core   +1 more source

Emerging Memory and Device Technologies for Hardware‐Accelerated Model Training and Inference

Advanced Electronic Materials, EarlyView.
This review investigates the suitability of various emerging memory technologies as compute‐in‐memory hardware for artificial intelligence (AI) applications. Distinct requirements for training‐ and inference‐centric computing are discussed, spanning device physics, materials, and system integration.
Yoonho Cho, Dae‐won Kim, Yujin Kim, Jung‐Heum Na, Yuwon Jeong, Dong‐Yeop Lee, Shinhyun Choi   +6 more
wiley   +1 more source

Recurrent neural network (RNN).

, 2016
A trained RNN of excitatory and inhibitory rate units r(t) receives time-varying inputs u(t) and produces the desired time-varying outputs z(t). Inputs encode task-relevant sensory information or internal rules, while outputs indicate a decision in the ...
Guangyu R. Yang (2543947), Xiao-Jing Wang (71345), H. Francis Song (2543944)   +2 more
core   +1 more source

Hybrid Deep Learning Model for Heart Disease Prediction Using Recurrent Neural Network (RNN)

, 2023
In this paper, we use a recurrent neural network (RNN) that combines multiple gated recurrent units (GRUs), long short-term memory (LSTM), and the Adam optimizer to develop a new hybrid deep learning model for heart disease prediction.
Omankwu, Obinnaya Chinecherem & Ubah, Valetine Ifeanyi
core   +1 more source

Machine learning driven many‐objective moving horizon scheduling optimization

AIChE Journal, EarlyView.
Abstract Industrial electrification can decarbonize chemical manufacturing, but it exposes operations to volatile electricity prices and carbon intensities. This work develops a machine learning‐enhanced many‐objective moving horizon scheduling framework that predicts objective correlation groupings from 48‐hour price and emission‐intensity profiles ...
Hongxuan Wang, Andrew Allman
wiley   +1 more source

Peramalan Harga Emas Dunia Menggunakan Metode Recurrent Neural Network (RNN) [PDF]

, 2020
Pertumbuhan ekonomi suatu negara sangat dipengaruhi oleh peningkatan investasi pada negara tersebut. Masyarakat kecil maupun atas menggemari investasi karena dapat menjadi pemasukan tambahan bagi investor.
Dewi, Ludia Rosema
core