Upgrade to Pro — share decks privately, control downloads, hide ads and more …

文献紹介 / Structure-based Knowledge Tracing: An In...

Avatar for Atom Atom
May 06, 2021
0
93

文献紹介 / Structure-based Knowledge Tracing: An Influence Propagation View

Avatar for Atom

Atom

May 06, 2021
Tweet

More Decks by Atom

See All by Atom
文献紹介 / Knowledge Tracing with GNN
Avatar for Atom roraidolaurent
0
97
文献紹介 / Non-Intrusive Parametric Reduced Order Models withHigh-Dimensional Inputs via Gradient-Free Active Subspace
Avatar for Atom roraidolaurent
0
56
ニューラルネットワークのベイズ推論 / Bayesian inference of neural networks
Avatar for Atom roraidolaurent
2
2.8k
Graph Convolutional Networks
Avatar for Atom roraidolaurent
0
230
文献紹介 / A Probabilistic Annotation Model for Crowdsourcing Coreference
Avatar for Atom roraidolaurent
0
69
文献紹介Deep Temporal-Recurrent-Replicated-Softmax for Topical Trends over Time
Avatar for Atom roraidolaurent
0
100
文献紹介/ Bayesian Learning for Neural Dependency Parsing
Avatar for Atom roraidolaurent
0
120
ポッキー数列の加法定理 / Pocky number additon theorem
Avatar for Atom roraidolaurent
0
210
Scalable Bayesian Learning of Recurrent Neural Networks for Language Modeling
Avatar for Atom roraidolaurent
1
150

Featured

See All Featured
Leading Effective Engineering Teams in the AI Era
Avatar for Addy Osmani addyosmani
7
710
Rebuilding a faster, lazier Slack
Avatar for samanthasiow samanthasiow
84
9.2k
Unsuck your backbone
Avatar for Amy Palamountain ammeep
671
58k
Build The Right Thing And Hit Your Dates
Avatar for Maggie C. maggiecrowley
38
2.9k
Fireside Chat
Avatar for paigeccino paigeccino
41
3.7k
I Don’t Have Time: Getting Over the Fear to Launch Your Podcast
Avatar for Joe Casabona jcasabona
34
2.5k
Keith and Marios Guide to Fast Websites
Avatar for Keith Pitt keithpitt
412
23k
The Cult of Friendly URLs
Avatar for Andy Hume andyhume
79
6.7k
Large-scale JavaScript Application Architecture
Avatar for Addy Osmani addyosmani
514
110k
ReactJS: Keep Simple. Everything can be a component!
Avatar for Pedro Nauck pedronauck
666
130k
For a Future-Friendly Web
Avatar for Brad Frost brad_frost
180
10k
Designing for Performance
Avatar for Lara Hogan lara
610
69k

Transcript

  1. None

  2. 2

  3. 3

  4. 4

  5. 5

  6. 6

  7. 7

  8. 8

  9. 9

  10. 10 𝒙𝑡 = 𝑒𝑡 = 0に回答して不正解? 𝑒𝑡 = 0に回答して正解? 𝑒𝑡

    = 1に回答して不正解? ⋮ 関係r ごとに埋め込み 関係r に関する一時的に用いる特徴量 注）ℎ𝑖 𝑡 ← ℎ 𝑖 𝑡,𝑇と更新されない．

  11. 11 𝑝𝑎𝑟𝑡𝑖𝑗 𝑟

  12. 12

  13. 13

  14. 14

  15. 15

  16. 16

  17. 17

  18. 18

  19. 19

  20. 20

  21. 21

  22. 22

  23. 23 1ステップのみの学習で得られた 影響ベクトル 𝐽𝑖 ∈ ℝ+𝑁として 概念間の影響ベクトルのコサイン類似度が 0.5以上のものにエッジを引いてクラスタリング

  24. 24

  25. 25