Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Speaker Deck
PRO
Sign in
Sign up for free
文献紹介 / Structure-based Knowledge Tracing: An Influence Propagation View
Atom
May 06, 2021
0
44
文献紹介 / Structure-based Knowledge Tracing: An Influence Propagation View
Atom
May 06, 2021
Tweet
Share
More Decks by Atom
See All by Atom
文献紹介 / Knowledge Tracing with GNN
roraidolaurent
0
37
文献紹介 / Non-Intrusive Parametric Reduced Order Models withHigh-Dimensional Inputs via Gradient-Free Active Subspace
roraidolaurent
0
28
ニューラルネットワークのベイズ推論 / Bayesian inference of neural networks
roraidolaurent
1
2.4k
Graph Convolutional Networks
roraidolaurent
0
140
文献紹介 / A Probabilistic Annotation Model for Crowdsourcing Coreference
roraidolaurent
0
38
文献紹介Deep Temporal-Recurrent-Replicated-Softmax for Topical Trends over Time
roraidolaurent
0
63
文献紹介/ Bayesian Learning for Neural Dependency Parsing
roraidolaurent
0
71
ポッキー数列の加法定理 / Pocky number additon theorem
roraidolaurent
0
100
Scalable Bayesian Learning of Recurrent Neural Networks for Language Modeling
roraidolaurent
1
78
Featured
See All Featured
Three Pipe Problems
jasonvnalue
89
8.9k
The Art of Programming - Codeland 2020
erikaheidi
35
11k
"I'm Feeling Lucky" - Building Great Search Experiences for Today's Users (#IAC19)
danielanewman
217
21k
Optimizing for Happiness
mojombo
365
64k
CoffeeScript is Beautiful & I Never Want to Write Plain JavaScript Again
sstephenson
152
13k
StorybookのUI Testing Handbookを読んだ
zakiyama
8
3.2k
Design and Strategy: How to Deal with People Who Don’t "Get" Design
morganepeng
109
16k
ピンチをチャンスに:未来をつくるプロダクトロードマップ #pmconf2020
aki_iinuma
31
20k
Visualization
eitanlees
128
12k
CSS Pre-Processors: Stylus, Less & Sass
bermonpainter
349
27k
Fontdeck: Realign not Redesign
paulrobertlloyd
74
4.3k
Cheating the UX When There Is Nothing More to Optimize - PixelPioneers
stephaniewalter
270
12k
Transcript
None
2
3
4
5
6
7
8
9
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 𝑝𝑎𝑟𝑡𝑖𝑗 𝑟
12
13
14
15
16
17
18
19
20
21
22
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
25