Result for "Deep Learning",188
NTT コミュニケーション科学基礎研究所 オープンハウス2020
,” under review. T. Ngo, Z. Lu, G. Carneiro, “Combining deep learning and level set for the automated
https://www.rd.ntt/cs/event/openhouse/2020/exhibition21/
2019_booklet_english.pdf
estimation from spatiotemporal population data～ 04 Improving the accuracy of deep learning ～Larger capacity
https://www.rd.ntt/cs/event/openhouse/2019/download/2019_booklet_english.pdf
c_20.pdf
. Zhang, B. Kleijn,“Edge-consensus learning: deep learning on P2P networks with nonhomogeneous data
https://www.rd.ntt/cs/event/openhouse/2020/download/c_20.pdf
NTT Communication Science Laboratories Open House 2018
for language acquisition by infants. The remarkable progress of deep learning is representative of
https://www.rd.ntt/cs/event/openhouse/2018/talk/director/index_en.html
松尾 洋一
Deep Learning Model for Missing Data," 2021 IFIP/IEEE International Symposium on Integrated Network
https://www.rd.ntt/ns/qos/person/matsuo/
NTT コミュニケーション科学基礎研究所 オープンハウス2020
を自在に探し出して活用・操作可能にする仕組みの実現をめざします。 関連文献 O. Krishna, G. Irie, X. Wu, T. Kawanishi, K. Kashino, “Learning
https://www.rd.ntt/cs/event/openhouse/2020/exhibition19/
信号処理研究グループ｜NTTコミュニケーション科学基礎研究所｜NTT R&D Website
processing with deep-learning techniques," IEEE Signal Processing Magazine, vol. 36, no. 6, pp. 111-124, 2019
https://www.rd.ntt/cs/team_project/media/signal/
メディア情報研究部 過去のニュース｜NTTコミュニケーション科学基礎研究所｜NTT R&D Website
】金子特別研究員と東京大学による論文 “Frame-Level Event Representation Learning for Semantic-Level Generation and
https://www.rd.ntt/cs/team_project/media/past_news.html
スライド 1
ットが特定の人の声にのみ反応するなど、人とより自然に会話できるようになります。 16 Computational selective hearing based on deep learning [1] K
https://www.rd.ntt/cs/event/openhouse/2018/exhibition/16/poster16.pdf
スライド 1
ルネック解消で精度を向上 Larger capacity output function for deep learning ～深層学習における、より高い表現能力を持つ出力関数～深層学習による画像認識や機械翻訳
https://www.rd.ntt/cs/event/openhouse/2019/download/04_a.pdf
c_19.pdf
. Krishna, G. Irie, X. Wu, T. Kawanishi, K. Kashino,“Learning search path for region-level image matching
https://www.rd.ntt/cs/event/openhouse/2020/download/c_19.pdf
メディア認識研究グループ｜NTTコミュニケーション科学基礎研究所｜NTT R&D Website
Kenji Iwana, and Seiichi Uchida, "Attention to warp: Deep metric learning for multivariate time series
https://www.rd.ntt/cs/team_project/media/recognition/
スライド 1
に対して根拠を説明できることが必要となる応用分野においても、安心してDNNが使えるような未来をめざしています。 07 Interpreting deep learning from network
https://www.rd.ntt/cs/event/openhouse/2018/exhibition/7/poster7.pdf
スライド 1
learning [1] T. Koumura, H. Terashima, S. Furukawa,“Representation of amplitude modulation in a deep neural
https://www.rd.ntt/cs/event/openhouse/2018/exhibition/24/poster24.pdf
スライド 1
deep learning for mobile devices 05 深層学習をモバイル向けに小さくします～量子化による深層学習のモデル圧縮技術～画像や音声などの認識に深層学習が盛んに用い
https://www.rd.ntt/cs/event/openhouse/2018/exhibition/5/poster5.pdf
H1-H4
ています。関連文献プロフィールメディア情報研究部 Generative personal assistance with audio and visual examples Deep learning opens
https://www.rd.ntt/cs/event/openhouse/2017/talk/research2/talk_kaneko.pdf
Behavioral technology modeling | NTT R&D Website
approaches such as machine learning, mathematical optimization, and probability theory. The NTT Human
https://www.rd.ntt/e/hil/category/behavior_modeling/
Media Information Laboratory | NTT Communication Science Laboratories | NTT R&D Website
using machine learning-based periodic analysis” has been accepted to Astronomy and Computing. N. Chihara
https://www.rd.ntt/e/cs/team_project/media/
Keeping the Spatial Relationship of the Eye and Arm Constant is Important for Motor Learning. Research on Sensorimotor Control Reveals Brain Mechanisms Underlying Movement Control Interview: Naotoshi Abekawa, Distinguished Researcher｜NTT R&D Website
Keeping the Spatial Relationship of the Eye and Arm Constant is Important for Motor Learning
https://www.rd.ntt/e/basic_research/0003.html
talk_yoshioka.pdf
Advances in deep learning and signal processing that are making speech recognition leap forward 音声認識が人間に近づ
https://www.rd.ntt/cs/event/openhouse/2016/talk/research1/talk_yoshioka.pdf