Author

Fangzhou Lin

Tohoku UniversityORCID 0000-0002-1749-3599Unclaimed ORCID profile · follow to get notified of new preprints

Additional preprints under this name without ORCID

Fangzhou Lin1 paper · Fujian Medical University

Biology Disciplines

Click to filter author papers

Neuroscience· 2

Signature Assays, Organisms & Methods

Click to filter · or open tag

Research Focus:benchmarking· 1 Approach:deep learning· 1 Research Focus:sequence-to-function modeling· 1 Approach:statistical model· 1

Frequent Co-Authors

Kazunori D. YamadaiD· 2 shared Mohammad Samy Baladram· 1 shared Tsukasa NakamuraiD· 1 shared

Activity by Year

2020-2022 · peak 1/yr

Co-Author Collaboration Network

3 top collaborators · 2 mutual co-author links

Click any collaborator node to inspect or filter shared papers

Focal author (center)Selected co-authorORCID co-authorUnlinked name

Curved chords = mutual co-authorship

2 shared papersNeuroscience

Kazunori D. YamadaORCID

Mutual co-authors in cluster

Author profile →

2 papers

Recent·Most cited

NeuroscienceFrontiers in Artificial IntelligencePeer-reviewedOct 11, 2022

Relation is an option for processing context information

Kazunori D. Yamada, Mohammad Samy Baladram, Fangzhou Lin

This paper introduces a new mechanism called 'relation' that processes context information efficiently, achieving similar performance to attention mechanisms with lower time complexity.

2 citations

𝕏 PostBluesky

NeuroscienceInterdisciplinary Information SciencesPeer-reviewedSep 15, 2020

Developing a novel recurrent neural network architecture with fewer parameters and good learning performance

Kazunori D. Yamada, Fangzhou Lin, Tsukasa Nakamura

This paper develops a novel RNN architecture, YamRNN, with fewer parameters and faster learning performance compared to LSTM and GRU on sequence classification tasks.

21 citations

deep learningstatistical model

𝕏 PostBluesky