文献紹介 / Structure-based Knowledge Tracing: An Influence Propagation View

May 06, 2021

66

文献紹介 / Structure-based Knowledge Tracing: An Influence Propagation View

Atom

May 06, 2021

Tweet

More Decks by Atom

See All by Atom

文献紹介 / Knowledge Tracing with GNN

0

55

文献紹介 / Non-Intrusive Parametric Reduced Order Models withHigh-Dimensional Inputs via Gradient-Free Active Subspace

0

40

ニューラルネットワークのベイズ推論 / Bayesian inference of neural networks

1

2.6k

Graph Convolutional Networks

0

190

文献紹介 / A Probabilistic Annotation Model for Crowdsourcing Coreference

0

47

文献紹介Deep Temporal-Recurrent-Replicated-Softmax for Topical Trends over Time

0

74

文献紹介/ Bayesian Learning for Neural Dependency Parsing

0

81

ポッキー数列の加法定理 / Pocky number additon theorem

0

170

Scalable Bayesian Learning of Recurrent Neural Networks for Language Modeling

1

110

Featured

See All Featured

80

8.8k

Clear Off the Table

84

310k

Building Your Own Lightsaber

99

5.7k

YesSQL, Process and Tooling at Scale

164

13k

Atom: Resistance is Futile

259

25k

Raft: Consensus for Rubyists

132

6.3k

The Brand Is Dead. Long Live the Brand.

49

28k

What's in a price? How to price your products and services

237

11k

How to Create Impact in a Changing Tech Landscape [PerfNow 2023]

14

1.5k

Practical Orchestrator

182

9.7k

Keith and Marios Guide to Fast Websites

408

22k

Imperfection Machines: The Place of Print at Facebook

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