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 Influence Propagation View
Search
Atom
May 06, 2021
0
66
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
55
文献紹介 / Non-Intrusive Parametric Reduced Order Models withHigh-Dimensional Inputs via Gradient-Free Active Subspace
roraidolaurent
0
40
ニューラルネットワークのベイズ推論 / Bayesian inference of neural networks
roraidolaurent
1
2.6k
Graph Convolutional Networks
roraidolaurent
0
190
文献紹介 / A Probabilistic Annotation Model for Crowdsourcing Coreference
roraidolaurent
0
47
文献紹介Deep Temporal-Recurrent-Replicated-Softmax for Topical Trends over Time
roraidolaurent
0
74
文献紹介/ Bayesian Learning for Neural Dependency Parsing
roraidolaurent
0
81
ポッキー数列の加法定理 / Pocky number additon theorem
roraidolaurent
0
170
Scalable Bayesian Learning of Recurrent Neural Networks for Language Modeling
roraidolaurent
1
110
Featured
See All Featured
BBQ
matthewcrist
80
8.8k
Clear Off the Table
cherdarchuk
84
310k
Building Your Own Lightsaber
phodgson
99
5.7k
YesSQL, Process and Tooling at Scale
rocio
164
13k
Atom: Resistance is Futile
akmur
259
25k
Raft: Consensus for Rubyists
vanstee
132
6.3k
The Brand Is Dead. Long Live the Brand.
mthomps
49
28k
What's in a price? How to price your products and services
michaelherold
237
11k
How to Create Impact in a Changing Tech Landscape [PerfNow 2023]
tammyeverts
14
1.5k
Practical Orchestrator
shlominoach
182
9.7k
Keith and Marios Guide to Fast Websites
keithpitt
408
22k
Imperfection Machines: The Place of Print at Facebook
scottboms
260
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