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

May 06, 2021

70

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

70

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

0

41

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

200

文献紹介 / A Probabilistic Annotation Model for Crowdsourcing Coreference

0

52

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

0

80

文献紹介/ Bayesian Learning for Neural Dependency Parsing

0

85

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

0

180

Scalable Bayesian Learning of Recurrent Neural Networks for Language Modeling

1

120

Featured

See All Featured

Design by the Numbers

277

19k

Code Reviewing Like a Champion

517

39k

Six Lessons from altMBA

26

3.4k

Responsive Adventures: Dirty Tricks From The Dark Corners of Front-End

248

20k

Helping Users Find Their Own Way: Creating Modern Search Experiences

29

2.2k

Designing Experiences People Love

138

23k

Thoughts on Productivity

66

4.2k

Navigating Team Friction

183

13k

Code Review Best Practice

62

16k

Producing Creativity

340

39k

GraphQLの誤解/rethinking-graphql

65

9.8k

sergeychernyshev

22

430

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