Excellence Sharing Growth

2018. 10. 11-12 COEX Grand Ballroom, Seoul

Scroll icon
See you next year!

DEVIEW 2018 행사가 종료되었습니다.

발표 영상과 자료를 지금 확인해보세요.

WATCH VIDEOS
2018 DEVIEW 행사 사진
2018 DEVIEW 행사 사진
2018 DEVIEW 행사 사진
2018 DEVIEW 행사 사진
2018 DEVIEW 행사 사진
2018 DEVIEW 행사 사진
2018 DEVIEW 행사 사진
2018 DEVIEW 행사 사진
2018 DEVIEW 행사 사진
2018 DEVIEW 행사 사진
2018 DEVIEW 행사 사진
2018 DEVIEW 행사 사진
2018 DEVIEW 행사 사진

SESSIONS

강연 목록

강연자 사진
강연 분야
  • 머신러닝
  • AI
강연 제목
Deep Learning to help student’s Deep Learning
강연 내용
With the growing demand for people to keep learning throughout their careers, massive open online course (MOOCs) companies, such as Udacity and Coursera, not only aggressively design new courses that are relevant (e.g., self-driving cars and flying cars), but refresh existing courses’ content frequently to keep them up-to-date. This effort results in a significant increase in student numbers, which makes it impractical for even experienced human instructors to assess an individual student's level of engagement and anticipate their learning outcomes. Moreover, students in each MOOC classroom are heterogeneous in background and intention, which is very different from a classic classroom. Even subsequent offerings of a course within a year will have a different population of students, mentors, and—in some cases—instructors. Also, due to the nascent nature of online learning platforms, many other aspects of a course will evolve quickly such that students are frequently being exposed to experimental content modalities or workflow refinements. In this world of MOOCs, an automated machine which reliably forecasts students’ performance in real-time (or early stages), would be a valuable tool for making smart decisions about when (and with whom) to make live educational interventions as students interact with online coursework, with the aim of increasing engagement, providing motivation, and empowering students to succeed. With that, in this talk, we first recast the student performance prediction problem as a sequential event prediction problem. Then introduce recently-developed GritNet architecture which is the current state of the art for student performance problem and develop methods to use (or operationalize) GritNet in real-time or live predictions with on-going courses. Our results for real Udacity students’ graduation predictions demonstrate that the GritNet not only generalizes well from one course to another across different Nanodegree programs, but enhances real-time predictions explicitly in the first few weeks when accurate predictions are most challenging. In contrast to prior works, the GritNet does not need any feature engineering and it can operate on any student event data associated with a timestamp.
강연자
김병학
전체 Schedule 보러가기

PARTNERS

  • baidu
  • carnegie mellon university
  • logo_coupang
  • google
  • hyper connect
  • imply
  • labs
  • labs europe
  • line
  • lunit
  • naver
  • naver business platform
  • nvidia
  • samsunginternet
  • superb ai
  • theori
  • udacity
  • urbanbase

LOCATION

장소
코엑스 그랜드볼룸 (Coex Grand Ballroom)
주소
서울 강남구 영동대로 513 코엑스, (지번) 삼성동 159 코엑스
연락처
02-6000-0114

그랜드볼룸은 봉은사 맞은편 코엑스 1층 북문 쪽에 위치해 있습니다.
지하철 이용 시 9호선 봉은사역 7번 출구를 이용하시거나 삼성역 6번 출구를 이용하시면 됩니다.

교통정보 더보기 >

DEVIEW 2018에 관하여 더 궁금한 점이 있다면?

FAQ 보러가기