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 / Knowledge Tracing with GNN
Search
Atom
December 04, 2020
110
0
Share
文献紹介 / Knowledge Tracing with GNN
文献紹介と書いてあるが自分の用のメモ
公開しなくても良いかなと思ったが公開
Atom
December 04, 2020
More Decks by Atom
See All by Atom
文献紹介 / Structure-based Knowledge Tracing: An Influence Propagation View
roraidolaurent
0
110
文献紹介 / Non-Intrusive Parametric Reduced Order Models withHigh-Dimensional Inputs via Gradient-Free Active Subspace
roraidolaurent
0
67
ニューラルネットワークのベイズ推論 / Bayesian inference of neural networks
roraidolaurent
2
2.9k
Graph Convolutional Networks
roraidolaurent
0
250
文献紹介 / A Probabilistic Annotation Model for Crowdsourcing Coreference
roraidolaurent
0
84
文献紹介Deep Temporal-Recurrent-Replicated-Softmax for Topical Trends over Time
roraidolaurent
0
130
文献紹介/ Bayesian Learning for Neural Dependency Parsing
roraidolaurent
0
140
ポッキー数列の加法定理 / Pocky number additon theorem
roraidolaurent
0
270
Scalable Bayesian Learning of Recurrent Neural Networks for Language Modeling
roraidolaurent
1
170
Featured
See All Featured
Evolving SEO for Evolving Search Engines
ryanjones
0
180
Easily Structure & Communicate Ideas using Wireframe
afnizarnur
194
17k
My Coaching Mixtape
mlcsv
0
99
GitHub's CSS Performance
jonrohan
1032
470k
Applied NLP in the Age of Generative AI
inesmontani
PRO
4
2.2k
State of Search Keynote: SEO is Dead Long Live SEO
ryanjones
0
180
How to Talk to Developers About Accessibility
jct
2
180
Fantastic passwords and where to find them - at NoRuKo
philnash
52
3.6k
What's in a price? How to price your products and services
michaelherold
247
13k
How STYLIGHT went responsive
nonsquared
100
6.1k
Claude Code どこまでも/ Claude Code Everywhere
nwiizo
64
55k
HU Berlin: Industrial-Strength Natural Language Processing with spaCy and Prodigy
inesmontani
PRO
0
320
Transcript
None
None
∈ , ∈ {0,1}2 ∈ {0,1} ∈ {0,1} + 1
≡ +1 = , , , = 1 , ⋯ , ⊆ × , ∈ ℝ× ∈ ∈ ℝ
None
∈ ℝ2× ∈ ℝ× () ∈ ℝ ∈
, ℎ
None
None
None
None
None
None
☓
None
None
∈ {0,1}
None
None
None
−1 から問題 (スキル をもつ)に正答確率を アテンションで求めるが, と同じスキルをもつ問題(例 )
の正誤情報 は −1 では失われている可能性が大きい. に関連する問題を選択し, その情報 についても アテンションをとる.
None
None
None
None
None
None
None