| Tifani Warnita, Nakamasa Inoue, and Koichi Shinoda. |
Detecting alzheimer's disease using gated convolutional neural network from audio data. Proc. Interspeech. 2018. |
| Jiacen Zhang, Nakamasa Inoue, and Koich Shinoda. |
I-vector transformation using conditional generative adversarial networks for short utterance speaker verification. Proc. Interspeech. 2018. |
| 金井 怜, 井上 中順, 李 時旭, 篠田 浩一. |
単語分散表現を用いた動画からのイベント検出. 第21回 画像の認識・理解シンポジウム (MIRU). 2018. |
| Conggui Liu, Nakamasa Inoue, and Koichi Shinoda. |
A unified network for multi-speaker speech recognition with multi-channel recordings. Proc. APSIPA. 2017. |
| Thao-Minh Le, Nakamasa Inoue, and Koichi Shinoda. |
A fine-to-coarse convoluational neural network for 3d human action recognition. Proc. British Machine Vision Conference (BMVC). 2018. |
| Yan Long, Nakamasa Inoue, Koichi Shinoda, Yoichi Yatsu, Ryosuke Itoh, Nobuyuki Kawai |
Astronomical Image Subtraction for Transient Detection Using CNN, 第21回 画像の認識・理解シンポジウム (MIRU). 2018. |
| 正田 惇修, 井上 中順, 篠田 浩一. |
弱ラベル付きデータを用いた動画からのイベント検出. |
| Raden Muhammad Mu'az, Nakamasa Inoue, and Koichi Shinoda. |
Sequence-Level Knowledge Distillation for Model Compression of Attention-Based Sequence-To-Sequence Speech Recognition. |
| Yuji Kuwamura |
Acceleration of Natural Gradient Descent Using Kronecker Factorizatoin |
| Hiroki Naganuma |
Smoothing of the Objective Function in Stochastic Optimization for Large Scale Parallel Learning |
| Hiroyuki Otomo |
Distributed Deep Learning Using Natural Gradient Descent |
| Chenwu Zhang |
Acceleration of the Fast Multipole Methods by Exploiting Symmetry of the Octree |
| Sameer Deshmukh |
MPI Parallelization of Hierarchical Low-Rank Matrices |
| Peter Spalthof |
C++ Framework for Simplifying Hierarchical Low-Rank Matrix Operations |
| Yuki Ito |
Runtime GPU Memory Optimization for Supporting Large Neural Networks on Chainer |
| Arie Wahyu, Jun Jin Choong, Kaushalya Madhawa and Tsuyoshi Murata |
Towards Robust Compressed Convolutional Neural Networks |
| Jun Jin Choong, Xin Liu & Tsuyoshi Murata |
Learning Community Structure with Variational Autoencoder |
| Hiep Le and Tsuyoshi Murata |
Deep Modular Multimodal Fusion on Multiple Sensors for Volcano Activity Recognition |
| Arie Wahyu and Tsuyoshi Murata |
Learning Adaptive Graph Protection Strategy on Dynamic Networks via Reinforcement Learning |
| Kaushalya Madhawa and Tsuyoshi Murata |
Exploring Partially Observed Networks with Nonparametric Bandits |
| Peng Chen |
Efficient Algorithms for the Summed Area Tables Primitive on GPUs |
| Shweta Salaria, Aleksandr Drozd, Artur Podobas and Satoshi Matsuoka |
Predicting Performance Using Collaborative Filtering |
| Jian Guo |
Underestimation Predictions of Job Runtime on HPC System using Machine Learning |
| Mateusz Bysiek |
Between Python and performance |
| Kazuaki Matsumura |
Compilation and Quantitative Approach Towards Loop Optimizations: A Case of Stencil Computation |
| Yohei Tsuji, Kazuki Osawa, Yuichiro Ueno, Akira Naruse, Rio Yokota, Satoshi Matsuoka |
Accelerating Deep Learning with Distributed Computation and Second-Order Optimization |
| Yosuke Oyama, Tal Ben-Nun, Torsten Hoefler, Satoshi Matsuoka |
μ-cuDNN: Accelerating Deep Learning Frameworks with Micro-Batching |
| 大山洋介, 野村哲弘, 佐藤育郎, 松岡聡 |
大規模並列環境における低精度型を用いたディープラーニングの学習精度の検証 |
| Kevin A. Brown, Nikhil Jain, Satoshi Matsuoka, Martin Schulz, Abhinav Bhatele |
A Deeper Understanding of Data Movement Bottlenecks on Fat-tree Networks |
|
Hiroki Kanezashi, Toyotaro Suzumura, Dario Garcia-Gasulla, Min-Hwan and Satoshi Matsuoka
|
Adaptive Pattern Matching with Reinforcement Learning for Dynamic Graphs
|
|
Haoyu Zhang, Mohamed Wahib, Peng Chen and Satoshi Matsuoka.
|
Can Local Binary Convolutions Really Make Neural Networks Models Smaller?
|
|
Ryan Barton1, Mohamed Wahib, Artur Podobas and Satoshi Matsuoka
|
BITFLEX: A Dynamic Runtime Library for Bit-Level Precision Manipulation and Approximate Computing
|
|
Peng Chen, Mohamed Wahib, Shinichiro Takizawa and Satoshi Matsuoka
|
Pushing the Limits for 2D Convolution Computation On CUDA-enabled GPUs
|
|
Yusuke Nagasaka, Akira Nukada, Ryosuke Kojima and Satoshi Matsuoka.
|
Batched SpMM for Accelerating GCN Application.
|
|
Artur Podobas and Satoshi Matsuoka
|
Towards Numerical Precision Exploration of Deep-Learning using FPGAs
|
|
八島慶汰、大山洋介、松岡聡
|
深層学習におけるBatchNormalization使用時の計算時間と精度の関係性
|
|
土川 稔生, 大山洋介, 野村 哲弘, 松岡聡
|
機械学習による計算機トレースの自動生成
|