日本語
Virtual Reality as a User-friendly Interface for Learning from Demonstration
We use Virtual Reality as an intuitive interface for Imitation Learning to supervise a deep neural network based visual attention model.
Hierarchical Attention Model
Applications such as human-robot interaction (HRI) and autonomous driving requires the agent to focus at high resolution on subtle visual cues for achieving proficiency. Existing vision systems have hardware limitations to achieve such high resolution and perform poorly in real-world environments. Human vision overcomes this problem by relying on a foveal view coupled with an…
FacialVAE – Conditional VAE-GAN with Attribute Inference for Faces
A generative model for faces based on Conditional VAE-GAN. – M. Suzuki
Deep X-ray image processing for diagnosis support
Joint work with The University of Tokyo Hospital. CNN, VAE, Generative Models, etc. – K. Nakayama, et al.
GeSdA – GPU empowered Stacked denoising Autoencoder
High-performance Stacked denoising Autoencoder enhanced by CrossPre (Cross-Layer Pretraining). – K.Nakayama
Related Activities – Deeplearning.jp & AIL.tokyo
We are organising a special interest group on deep learning and several lecture series of deep learning – Deeplearning.jp | AIL.tokyo
Related Activities – HPC & GPU Computing
To enhance computational performance on deep learning algorithms, we are working on projects such as GPU system virtualization and distributed GPU computation models. We are also providing iLect, a GPU-enabled programming environment accessible by Web broseewsers. – iLect | HPC
Neural Darwinism
Evolutional deep learning algorithms towards flexible networks. – H. Kurotaki
Deep Activity Recognition for Wheelchairs
Sensors, CNN, Model Compression for limited resource environment. – Y. Iwasawa
Trend Prediction with Recurrent Neural Networks
TBA. – N. Nonaka, et al.