Result for "Deep Learning",316

スライド 1

スライド 1 Abstract References Contact オープンハウス 2020 20 Deep learning without data aggregation from

https://www.rd.ntt/cs/event/openhouse/2020/download/c_20_en.pdf

Problem Solving Will Not Reduce the Number of Research Themes―It Will Open up New Research Areas | NTT R&D Website

artificial intelligence (AI) started around 2012, since then, neural networks based on deep learning have

https://www.rd.ntt/e/research/JN202203_17523.html

Getting closer to humans with AI and understanding humans with brain science: AI with a deep understanding of people, capable of coexisting with us｜NTT R&D Website

to near and surpass specific human abilities through research into fields such as deep learning

https://www.rd.ntt/e/ai/0003.html

Takuhiro Kaneko | NTT R&D Website

2020), Oct. 2020. Keywords Image Synthesis, Speech Synthesis, Voice Conversion, Machine Learning, Deep

https://www.rd.ntt/e/organization/researcher/special/s_046.html

Phygital-data-centric Computing | NTT R&D Website

computational load. In response to this issue, we developed Carrier Cloud for Deep Learning, which accommodates

https://www.rd.ntt/e/research/JN20191110_h.html

Hirokazu Kameoka | NTT R&D Website

, deep learning More Research Activity Related Contents

https://www.rd.ntt/e/organization/researcher/superior/s_025.html

F12_leaf_e.pdf

Through understanding deep learning models, we enhance their fairness and safety Understanding the

https://www.rd.ntt/forum/2023/doc/F12_leaf_e.pdf

G03-01-e.pdf

device control. (1) A deep learning model with a phase token to capture timing in motor imagery changes

https://www.rd.ntt/forum/2024/doc/G03-01-e.pdf

Reach Out and Touch Someone’s Heart: Exploring the Essence of Communication to Create a Spiritually Rich Society｜NTT R&D Website

, especially deep learning, a massive increase in data and the need to protect privacy are generating a need to

https://www.rd.ntt/e/research/JN202107_14463.html

スライド 1

degradation. On the other hand, the proposed method, which is based purely on deep learning, can theoretically

https://www.rd.ntt/cs/event/openhouse/2019/download/17_c_en.pdf

スライド 1

listen to - Computational selective hearing based on deep learning - Use a few seconds of speech from the

https://www.rd.ntt/cs/event/openhouse/2018/exhibition/16/poster_en_16.pdf

Learning 3D Information from 2D Images Using Aperture Rendering Generative Adversarial Networks toward Developing a Computer that "Understands the 3D World" | NTT R&D Website

. We spoke to Takuhiro Kaneko, a distinguished researcher who developed a novel deep learning model

https://www.rd.ntt/e/research/JN202205_18199.html

NTT Communication Science Laboratories Open House 2017

) representation, and a deep learning-based approach using the generative adversarial network (GAN). The former

https://www.rd.ntt/cs/event/openhouse/2017/exhibition/17/index_en.html

スライド 1

learning Our goal is to automatically discover “causal relationships” from time series data, i.e., a

https://www.rd.ntt/cs/event/openhouse/2019/download/05_a_en.pdf

スライド 1

signals with similar voice characteristics  SpeakerBeam （= Selective Hearing based on Deep Learning） Deep

https://www.rd.ntt/cs/event/openhouse/2020/download/c_17_en.pdf

The Future of Data Distribution and Its Security Technology | NTT R&D Website

process a standard algorithm used for deep learning, which has begun to be used in the AI field, without

https://www.rd.ntt/e/research/JN20200214_h.html

『NTT R&Dフォーラム 2018』開催報告　～デジタル技術が彩る未来へ～｜NTT R&D Website

シーの数値を近隣にいるタクシーの位置情報とともにマッピングしたつばめグループのカーナビ Deep Learningを短時間で低コストに行います（corevoを支える基盤技術：E15） 昨今、さま

https://www.rd.ntt/forum/forum2018.html

Kenta Niwa | NTT R&D Website

, Noboru Harada, Guoqiang Zhang, and W. Bastiaan Kleijn, "Edge-consensus Learning: Deep Learning on P2P

https://www.rd.ntt/e/organization/researcher/special/s_061.html

Developing AI that Pays Attention to Who You Want to Listen to: Deep-learning-based Selective Hearing with SpeakerBeam｜NTT R&D Website

Developing AI that Pays Attention to Who You Want to Listen to: Deep-learning-based Selective

https://www.rd.ntt/e/research/JN202107_14481.html

poster_en.pdf

learning～ [1] Y. Endo, H. Toda, K. Nishida, A. Kawanobe, “Deep feature extraction from trajectories for

https://www.rd.ntt/cs/event/openhouse/2016/exhibition/5/poster_en.pdf