文献紹介 / Structure-based Knowledge Tracing: An In...

May 06, 2021

76

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

77

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

0

47

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

1

2.7k

Graph Convolutional Networks

0

210

文献紹介 / A Probabilistic Annotation Model for Crowdsourcing Coreference

0

59

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

0

90

文献紹介/ Bayesian Learning for Neural Dependency Parsing

0

98

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

0

190

Scalable Bayesian Learning of Recurrent Neural Networks for Language Modeling

1

120

Featured

See All Featured

Fontdeck: Realign not Redesign

paulrobertlloyd

83

5.4k

How to Think Like a Performance Engineer

22

1.3k

The Cult of Friendly URLs

78

6.2k

Thoughts on Productivity

69

4.5k

Java REST API Framework Comparison - PWX 2021

28

8.4k

Optimizing for Happiness

376

70k

Building an army of robots

303

45k

29

14k

Visualizing Your Data: Incorporating Mongo into Loggly Infrastructure

45

9.4k

Build your cross-platform service in a week with App Engine

229

18k

Principles of Awesome APIs and How to Build Them.

126

17k

Building Flexible Design Systems

yeseniaperezcruz

328

38k

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