• 이름: 차금강(Cha Keum Gang)

• Github : https://github.com/chagmgang

• Facebook : https://www.facebook.com/profile.php?id=100002147815509

• Email : [email protected]

• Google Scholar : https://scholar.google.com/citations?user=tLYtx20AAAAJ&hl=ko

• Linkedin : https://www.linkedin.com/in/keumgang-cha-58100b227/

• Community Activated at : RL Korea, Tensorflow-KR, Kaggle Korea

• Interested in : Remote Sensing, Computer Vision, Foundation Model, Large Scale Deep Learning Model

• Another Github : RLOpensource, AlphaStarKor

• Reinforcement Learning Framework Based on Tensorflow

• OpenAI SpinningUp kr

• self supervised learning

• Programming Language - Python, Javascript(Only React), Go

• Framework - Django, Tensorflow, Pytorch, React.js

• DevOps - Kubernetes, Azure Devops, Azure Pipeline

• MLOps - Airflow, Mlflow

• Server - MySQL, tensorflow_model_server

• OS - MacOS, Window, Ubuntu 16.04

• Self supervised learning framework

With 160 A100 GPU, generating remote sensing foundation model.

• IMPALA, R2D2, Apex

• Policy Gradient algorithm implementation

• Actor Critic algorithm implementation

• Trust Region Policy Optimization implementation

• Proximal Policy Optimization implementation

• Multi Thread Proximal Policy Optimization implementation

• Deep Q Network(Nature 2015) implementation

• Double DQN implementation

• Dueling DQN implementation

• Double Dueling DQN implementation

• Prioritized Experience Replay

• Doule Dueling DQN with Prioritized Experience Replay

• Generative Adversarial Imitation Learning

• Distributional Perspective on Reinforcement Learning(C51)

• Distributional Reinforcement Learning with Quantile Regression(QR-DQN)

• Implicit Quantile Networks for Distributional Reinforcement Learning(IQN)

• PPO + Intrinsic Curiosity Modules

• Relational Deep Reinforcement Learning

• IMPALA-Scalable-Distributed-Deep-RL-with-Importance-Weighted-Actor-Learner-Architectures

• Word Embedding with tensorflow, gensim

• Document Embedding with tensorflow, gensim

• Sequence to Sequence Learning with Neural Networks

• Effective Approaches to Attention-based Neural Machine Translation

• Generative Adversarial Network

• Conditional Generative Adversarial Network

• Deep Convolutional Generative Adversarial Networks

• Atari Version of Generative Adverarial Imitation Learning on MoveTobeacon

• Atari Version of MoveToBeacon Actor Critic

• Atari Version of MoveToBeacon Proximal Policy Optimization

• DeepMind Version of MoveToBeacon Proximal Policy Optimization

• DeepMind Version of CollectMineralShards Proximal Policy Optimization

• Discription of Reinforcement Learning in StarCraft II

• mnist

• seq2seq

• word2vec

• doc2vec

• Make deep learning based rest api with django framework for recommendation system(search)

• Member of PG Travel

• Member of tensorflow_RL

• (2010.03 ~ 2014.02), Pusan National University(부산대학교), Mechanical Engineering, Undergraduate

• (2014.03 ~ 2016.02), Pusan National University(부산대학교), Mechanical Engineering, Robotics, Master Degree

    http://mclab.me.pusan.ac.kr/mclab/index.do

• (2016.07 ~ 2017.03), Korea Institute of Industrial Technology(한국생산기술연구원), Researcher

    Development Embedded based Robotics to used as Rehabilitation robot

• (2016.10 ~ 2017.09), Korea Advanced Instituted of Science and Technology, Researcher

    Development Embedded based IOT machines(Embedded Design, Programming, Data Collections)

• (2018.01 ~ 2019.12), Nerdfactory, Researcher

    Development Recommandation Algorithm using Deep Learning Methodology

• (2020.01 ~ 2021.06), Satreci, Research Engineer

• (2021.06 ~ ) SI Aanalytics, Machine Learning Engineer

• Machine Learning Crash Course(구글 머신러닝 단기집중 과정) 이수

• Machine Learning with Tensorflow on Google Cloud Platform(Coursera) 이수

• SMCSPO Based Force Estimation for Jetting Rate Control of 3D Printer Nozzle to Build a House

• Reaction Force Estimation of Hydraulic Servo System Using Sliding Perturbation Observer

• Evaluation of a Possibility of Estimation of Reaction Force of Simple Hydraulic System using Sliding Perturbation Observer

• 슬라이딩 섭동 관측기를 이용한 유압 서보 시스템의 반력 추정

• Robust Control Scheme Based Reaction Force Estimation and Bilateral Control of Hydraulic Servo Robot

• A Study on Deep Learning Based Sauvegrain Method for Measurement of Puberty Bone Age

• Performance of Recommender Systems: Based on Content Navigator and Collaborative Filtering

• Contrastive Multiview Coding with Electro-optics for SAR Semantic Segmentation

• RAIN-F+: The data-driven precipitation prediction model for integrated weather observations

• RAIN-F: A fusion dataset for rainfall prediction using convolutional neural network

• Predicting quantitative precipitation from global precipitation measurements using deep neural networks

• 2nd, HAAFOR Challenge 2020

• 세상에서 가장 간단한 Airflow 튜토리얼

• Pytorch와 TensorRT를 이용한 딥 러닝 추론 최적화

• Pytorch를 TensorRT로 변환하기 위한 환경 설정

• Horovod 모듈 사용하여 Pytorch Multi GPU 학습 효율적으로 하기

• Multi GPU with Pytorch (DistributedDataParallel)

• 2018.06 - DLCAT 1st

• 2018.07 - 에이전트를 부탁해

• 2018.08 - 인공지능 비즈니스 개발 컨퍼런스 2018

• 2018.09 - Reinforcement Learning Korea

• 2018.10 - 대덕대학교

• 2018.11 - IBS

• 2018.01 - Pytorch KR DevCon 2019

• 2018.02 - AI friends

• 2019.06 - DeepReward 101

• 2019.07 - DLCAT 2nd

• 2019.08 - DeepReward 101

• 2019.09 - Babel TOP

• 2019.11 - [공개SW개발자센터] 연합 커뮤니티 행사<Effective TensorFlow 2.0>

• 2019.11 - 딥리워드(IMPALA Implementation)

• 2019.12 - Global AI BootCamp in Busan

• 2020.02 - 설명 가능한 인공지능 [eXplainable AI, XAI] 개발과 산업별 적용방안