Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
文献紹介 / Structure-based Knowledge Tracing: An In...
Search
Atom
May 06, 2021
0
91
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
96
文献紹介 / Non-Intrusive Parametric Reduced Order Models withHigh-Dimensional Inputs via Gradient-Free Active Subspace
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
roraidolaurent
2
2.8k
Graph Convolutional Networks
roraidolaurent
0
230
文献紹介 / A Probabilistic Annotation Model for Crowdsourcing Coreference
roraidolaurent
0
69
文献紹介Deep Temporal-Recurrent-Replicated-Softmax for Topical Trends over Time
roraidolaurent
0
100
文献紹介/ Bayesian Learning for Neural Dependency Parsing
roraidolaurent
0
120
ポッキー数列の加法定理 / Pocky number additon theorem
roraidolaurent
0
210
Scalable Bayesian Learning of Recurrent Neural Networks for Language Modeling
roraidolaurent
1
150
Featured
See All Featured
How To Stay Up To Date on Web Technology
chriscoyier
791
250k
The Straight Up "How To Draw Better" Workshop
denniskardys
237
140k
XXLCSS - How to scale CSS and keep your sanity
sugarenia
248
1.3M
For a Future-Friendly Web
brad_frost
180
9.9k
The Invisible Side of Design
smashingmag
301
51k
Automating Front-end Workflow
addyosmani
1371
200k
The Language of Interfaces
destraynor
162
25k
Design and Strategy: How to Deal with People Who Don’t "Get" Design
morganepeng
132
19k
ReactJS: Keep Simple. Everything can be a component!
pedronauck
667
120k
Making the Leap to Tech Lead
cromwellryan
135
9.5k
Balancing Empowerment & Direction
lara
4
670
Principles of Awesome APIs and How to Build Them.
keavy
127
17k
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