Clik here to view.
Accelerating Deep Learning Workloads with the MN-Core Compiler
Introduction Research and development of deep learning based applications requires significant computational resources. PFN developed MN-Core, a highly specialized deep learning accelerator to speed up...
View ArticleClik here to view.
Distributed reinforcement learning in PFN
Introduction PFRL has been under development as the successor of ChainerRL. We also continue the research of distributed reinforcement learning in PFN. In this blog, we introduce our design, practice,...
View ArticleClik here to view.
Neural Network Architecture for Efficient Deep Hedging
This post is contributed by Shota Imaki, who was an intern and a part-time engineer at PFN. Japanese version is available here. I am Shota Imaki, a Ph.D. student majoring in theoretical physics....
View ArticleClik here to view.
First Release of PyNIF3D
We are excited to announce the release of PyNIF3D – an open-source PyTorch-based library for research on neural implicit functions (NIF)-based 3D geometry representation. PyNIF3D aims to accelerate...
View ArticleClik here to view.
Distributed reinforcement learning in PFN
Introduction PFRL has been under development as the successor of ChainerRL. We also continue the research of distributed reinforcement learning (RL) in PFN. In this blog, we introduce our design,...
View ArticleClik here to view.
Discovery of SARS-CoV-2 protease inhibitors using AI drug discovery technology
A pharmaceutical agent (in yellow) binding to the main protease of SARS-CoV-2 (in purple) to inhibit viral replication. Introduction The novel coronavirus disease (COVID-19) is currently expected to...
View ArticleClik here to view.
Four Dimensional CT Using Implicit Neural Representation
This post is contributed by Pragyan Shrestha, who was an intern at PFN. I am Pragyan Shrestha, a first year graduate student at University of Tsukuba. My research topic is 3D reconstruction from 2D...
View ArticleClik here to view.
Change Detection and its Variable Selection in Multivariate Time Series Using...
This article is contributed by Ryo Yuki, who worked for the 2021 PFN Summer Internship. Abstract I am Ryo Yuki, a Ph.D. candidate at the Department of Mathematical Informatics at the University of...
View ArticleClik here to view.
A Year with Apache Ozone
Why Apache Ozone? To address increasing data needs and new use cases in Preferred Networks, PFN, we have been seeking a new storage system that scales out pseudo-infinitely. The amount of data usage...
View ArticleClik here to view.
AI based Drug Design using Variational Autoencoder and Weighted Retraining
This article is contributed by Jinzhe Zhang, who worked for the 2021 PFN Summer Internship. Introduction The traditional drug discovery technique often involves a trial-and-error process and most of...
View Article