Machine Learning

Thonglek君のIEICE-EE研究会 (2021年5月) での発表

当研究室D1のKundjanasith Thonglek (Tem) 君が, 電子通信エネルギー技術研究会 (IEICE-EE) 2021年5月 にて下記の論文を発表しました: Kundjanasith Thonglek, Kohei Ichikawa, Kazufumi Yuasa, Tadatoshi Babasaki, “LSTM-based


当研究室D1のKundjanasith Thonglek (Tem) 君が,機械学習の応用に関する国際会議 19th IEEE International Conference on Machine Learning and Applications (ICMLA 2020) にて下記の論文を発表しました:

Ensembling Heterogeneous Models for Federated Learning

Federated learning trains a model on a centralized server using datasets distributed over a large number of edge devices. Applying federated learning ensures data privacy because it does not transfer local data from edge devices to the server. Existing federated learning algorithms assume that all deployed models share the same structure. However, it is often infeasible to distribute the same model to every edge device because of hardware limitations such as computing performance and storage space.

Retraining Quantized Neural Networks without Labeled Data

Running neural network models on edge devices is attracting much attention by neural network researchers since edge computing technology is becoming more powerful than ever. However, deploying large neural network models on edge devices is challenging due to the limitation in available computing resources and storage space. Therefore, model compression techniques have been recently studied to reduce the model size and fit models on resource-limited edge devices. Compressing neural network models reduces the size of a model, but also degrades the accuracy of the model since it reduces the precision of weights in the model.

Improving Resource Utilization of Data Center using LSTM

Data centers are centralized facilities where computing and networking hardware are aggregated to handle large amounts of data and computation. In a data center, computing resources such as CPU and memory are usually managed by a resource manager. The resource manager accepts resource requests from users and allocates resources to their applications. A commonly known problem in resource management is that users often request more resources than their applications actually use.