Code Monkey home page Code Monkey logo

Hi ๐Ÿ‘‹, I'm Hoe Sung Ryu

๐Ÿ”ฅ Current Position: Ph.D student in the Department of Artificial Intelligence at Korea University.

A brief description of my research

The purpose of my research is to enhance the capabilities of intelligence of machine learning by way of human-informed technology. Through its combination of the precision of machine learning with human input and values, we will be able to make more informed decisions and develop clear strategies and solutions to the challenges.

In our previous work, we ask how well humans and a deep neural network (DNN) predicted the emergency decision. We have shown that the DNN out-performed humans for early time points, but had an equal performance for later time points. With Grad-CAM visualization technics, we found that the DNN could focus on the meaningful features (steering wheel and hill ridge) but could not capture the time importance.

Hoe Sung Ryu's Projects

2021-nia-k-ict-ai-lecture icon 2021-nia-k-ict-ai-lecture

๋ณธ ๊ฐ•์˜๋Š” ์ธ๊ณต์ง€๋Šฅ ๊ด€๋ จํ•˜์—ฌ ๊ด€์‹ฌ ์žˆ๋Š” ์ผ๋ฐ˜์ธ 50๋ช…์„ ๋Œ€์ƒ์œผ๋กœ ์˜จ๋ผ์ธ๊ต์œก์œผ๋กœ ์ง„ํ–‰๋˜๋ฉฐ ๊ต์œก์€ ํŒ๊ต ์Šคํƒ€ํŠธ์—…์บ ํผ์Šค 1๋™ 6์ธต์— ์†Œ์žฌํ•œ '๋น…๋ฐ์ดํ„ฐ์„ผํ„ฐ' ๊ต์œก์žฅ์—์„œ ๊ฐ•์˜๊ฐ€ ์ง„ํ–‰๋ฉ๋‹ˆ๋‹ค. ๊ฐ•์˜๋Š” 3์ผ๊ฐ„, ์˜ค์ „ 10์‹œ~์˜คํ›„ 6์‹œ๊นŒ์ง€(์ด 21์‹œ๊ฐ„) ๊ณผ์ •์œผ๋กœ ์ง„ํ–‰๋˜๋ฉฐ, ์ด๋ก ๊ณผ ์‹ค์Šต๊ณผ์ •์œผ๋กœ ์šด์˜๋ฉ๋‹ˆ๋‹ค.

ai_paper_review icon ai_paper_review

๊นŒ๋จน์œผ๋ฉด ๋‹ค์‹œ ๋ณด๋ ค๊ณ  ์ •๋ฆฌํ•ฉ๋‹ˆ๋‹ค.

bio_rnn_mem icon bio_rnn_mem

Predict sequential data with recurrent neural networks with biological wiring

echotorch icon echotorch

A Python toolkit for Reservoir Computing and Echo State Network experimentation based on pyTorch. EchoTorch is the only Python module available to easily create Deep Reservoir Computing models.

ijepa icon ijepa

Official codebase for I-JEPA, the Image-based Joint-Embedding Predictive Architecture. First outlined in the CVPR paper, "Self-supervised learning from images with a joint-embedding predictive architecture."

intel-image-classification icon intel-image-classification

[ Intel ] Keras๋ฅผ ์ด์šฉํ•˜์—ฌ ์—ฌ๋Ÿฌ๊ฐ€์ง€ ๋ฐ์ดํ„ฐ์…‹์„ ํ•™์Šต ํ›„ ๋‹ค์–‘ํ•œ CNN๋ชจ๋ธ์„ ํ†ตํ•ด์„œ ์ด๋ฏธ์ง€ ๋ถ„๋ฅ˜๋ฅผ ํ•˜๋Š” ํŠœํ† ๋ฆฌ์–ผ์ž…๋‹ˆ๋‹ค. ๋˜ํ•œ ๋งˆ์ง€๋ง‰์—” OpenVINO๋ฅผ ์ด์šฉํ•˜์—ฌ ์ถ”๋ก ํ•˜๋Š” ์˜ˆ์ œ ์ฝ”๋“œ์ž…๋‹ˆ๋‹ค

koreavpn icon koreavpn

Automator๋ฅผ ์ด์šฉํ•ด Mac์—์„œ ์‚ฌ์šฉํ•˜๋Š” VPN ์–ดํ”Œ ๋งŒ๋“ค๊ธฐ

lstm_rnn_tutorials_with_demo icon lstm_rnn_tutorials_with_demo

LSTM-RNN Tutorial with LSTM and RNN Tutorial with Demo with Demo Projects such as Stock/Bitcoin Time Series Prediction, Sentiment Analysis, Music Generation using Keras-Tensorflow

mimicry icon mimicry

[CVPR 2020 Workshop] A PyTorch GAN library that reproduces research results for popular GANs.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.