Results 61 to 70 of about 296,489 (278)
Segmental Recurrent Neural Networks
, 2015 We introduce segmental recurrent neural networks (SRNNs) which define, given an input sequence, a joint probability distribution over segmentations of the input and labelings of the segments. Representations of the input segments (i.e., contiguous subsequences of the input) are computed by encoding their constituent tokens using bidirectional recurrent
Lingpeng Kong, Chris Dyer, Noah A. Smith
openaire +2 more sources
Linked Recurrent Neural Networks
CoRR, 2018 Recurrent Neural Networks (RNNs) have been proven to be effective in modeling sequential data and they have been applied to boost a variety of tasks such as document classification, speech recognition and machine translation. Most of existing RNN models have been designed for sequences assumed to be identically and independently distributed (i.i.d ...
Zhiwei Wang 0001 +3 more
openaire +2 more sources
Multistability in Recurrent Neural Networks [PDF]
SIAM Journal on Applied Mathematics, 2006 Stable stationary solutions correspond to memory capacity in the application of associative memory for neural networks. In this presentation, existence of multiple stable stationary solutions for Hopfield-type neural networks with delay and without delay is investigated. Basins of attraction for these stationary solutions are also estimated.
Chang-Yuan Cheng +2 more
openaire +1 more source
Diversity and complexity in neural organoids
FEBS Letters, EarlyView.Neural organoid research aims to expand genetic diversity on one side and increase tissue complexity on the other. Chimeroids integrate multiple donor genomes within single organoids. Self‐organising multi‐identity organoids, exogenous cell seeding, or enforced assembly of region‐specific organoids contribute to tissue complexity.
Ilaria Chiaradia, Madeline A. Lancaster
wiley +1 more source
Grounded Recurrent Neural Networks
CoRR, 2017 In this work, we present the Grounded Recurrent Neural Network (GRNN), a recurrent neural network architecture for multi-label prediction which explicitly ties labels to specific dimensions of the recurrent hidden state (we call this process "grounding"). The approach is particularly well-suited for extracting large numbers of concepts from text.
Ankit Vani +2 more
openaire +2 more sources
Stochastic graph recurrent neural network
Neurocomputing, 2022 Representation learning over graph structure data has been widely studied due to its wide application prospects. However, previous methods mainly focus on static graphs while many real-world graphs evolve over time. Modeling such evolution is important for predicting properties of unseen networks.
Tijin Yan +3 more
openaire +2 more sources
FEBS Letters, EarlyView.Embryo‐like structures (stembryos) are an innovative tool, but they are hindered by experimental variability and limited developmental potential. DNA methylation is crucial for mammalian development, but its status in stembryo models is poorly characterized.
Sara Canil +4 more
wiley +1 more source
VGM-RNN: Recurrent Neural Networks for Video Game Music Generation [PDF]
, 2018 The recent explosion of interest in deep neural networks has affected and in some cases reinvigorated work in fields as diverse as natural language processing, image recognition, speech recognition and many more.
Mauthes, Nicolas
core +1 more source
Potential therapeutic targeting of BKCa channels in glioblastoma treatment
Molecular Oncology, EarlyView.This review summarizes current insights into the role of BKCa and mitoBKCa channels in glioblastoma biology, their potential classification as oncochannels, and the emerging pharmacological strategies targeting these channels, emphasizing the translational challenges in developing BKCa‐directed therapies for glioblastoma treatment.
Kamila Maliszewska‐Olejniczak +4 more
wiley +1 more source
, 2017 Clinical measurements that can be represented as time series constitute an important fraction of the electronic health records and are often both uncertain and incomplete.
Bianchi, Filippo Maria +5 more
core +1 more source