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
Sponsored
·
Your Podcast. Everywhere. Effortlessly.
Share. Educate. Inspire. Entertain. You do you. We'll handle the rest.
→
Atom
May 06, 2021
0
100
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
100
文献紹介 / Non-Intrusive Parametric Reduced Order Models withHigh-Dimensional Inputs via Gradient-Free Active Subspace
roraidolaurent
0
62
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
250
文献紹介 / A Probabilistic Annotation Model for Crowdsourcing Coreference
roraidolaurent
0
79
文献紹介Deep Temporal-Recurrent-Replicated-Softmax for Topical Trends over Time
roraidolaurent
0
120
文献紹介/ Bayesian Learning for Neural Dependency Parsing
roraidolaurent
0
130
ポッキー数列の加法定理 / Pocky number additon theorem
roraidolaurent
0
250
Scalable Bayesian Learning of Recurrent Neural Networks for Language Modeling
roraidolaurent
1
170
Featured
See All Featured
Raft: Consensus for Rubyists
vanstee
141
7.3k
A Modern Web Designer's Workflow
chriscoyier
698
190k
It's Worth the Effort
3n
188
29k
ラッコキーワード サービス紹介資料
rakko
1
2.4M
Side Projects
sachag
455
43k
Building AI with AI
inesmontani
PRO
1
740
New Earth Scene 8
popppiees
1
1.6k
Jamie Indigo - Trashchat’s Guide to Black Boxes: Technical SEO Tactics for LLMs
techseoconnect
PRO
0
75
Bootstrapping a Software Product
garrettdimon
PRO
307
120k
jQuery: Nuts, Bolts and Bling
dougneiner
65
8.4k
Visualization
eitanlees
150
17k
A designer walks into a library…
pauljervisheath
210
24k
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