Deep Learning


We, the Deep Learning research group of WEBLAB, are developing the future of artificial intelligence technologies. Our activities cover not only researches but also education and development.

Research Topics

FacialVAE – Conditional VAE-GAN with Attribute Inference for Faces

A generative model for faces based on Conditional VAE-GAN. Demo – M. Suzuki

vaegan

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.

Realtime Instance Recognition for Desktop Objects

TBA – K. Nakayama, et al.

Trend Prediction with Recurrent Neural Networks

TBA. – N. Nonaka, et al.

Deep Activity Recognition for Wheelchairs

Sensors, CNN, Model Compression for limited resource environment. – Y. Iwasawa

Neural Darwinism

Evolutional deep learning algorithms towards flexible networks. – H. Kurotaki

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

ail

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