原创 2019.11.5 note
2019.11.5 note Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer They propose a fr
2020-06-29 01:09:46
原创 2019.11.15 note (2)
2019.11.15 note (2) Intriguing properties of neural networks DeepFool: a simple and accurate method to fool deep
2020-06-29 01:09:36
原创 2019.11.6 note
2019.11.6 note DeepGCNs: Making GCNs Go as Deep as CNNs Graph Convolutional Networks (GCNs) offer an alternative th
2020-06-29 01:09:36
原创 2019.11.15 note (1)
2019.11.15 note (1) EXPLAINING AND HARNESSING ADVERSARIAL EXAMPLES FGSM (Fast Gradient Sign Method) Adversarial
2020-06-29 01:09:36
原创 IMO 2017 T1解答
Puzzle欄目開通 生活中經常做到有意思的題目，自己也會有些巧妙的解法。當時不記下來很快會忘記，非常可惜。所以我在博客裏開了Puzzle這個欄目，記錄有意思的謎題。那麼這個欄目的第一題，就獻給今天早上剛剛出爐的IMO 2017吧
2020-02-21 13:51:43
2
原创 2019.12.17 note
2019.12.17 note Filter Response Normalization Layer: Eliminating Batch Dependence in the Training of Deep Neural Ne
2020-02-21 13:51:43
原创 計算學習理論基礎
計算學習理論基礎 基礎知識 與計算理論類似，機器學習也有PAC可辨識，PAC可學習，高效PAC可學習的概念。 有限假設空間 在有限假設空間情形下，可以對PAC學習的樣本複雜度在可分，不可分，不可知情形下做出估計。 VC維
2020-02-21 13:51:43
1
原创 2020.1.13 note
2020.1.13 note AdderNet: Do We Really Need Multiplications in Deep Learning? Compared with cheap addition operation
2020-02-21 13:51:43
原创 VC維的幾個習題
VC維的幾個習題 線性分類假設空間的VC維 VCH(Rd)=d+1 ，H爲線性假設空間。 這是西瓜書上的一個習題，在學習計算理論的時候我也在博客上記過這個結論，二維的線性空間VC維爲3，(4的時候異或類的標號就打不散)也十分顯然
2020-02-21 13:51:43
原创 2019.12.13 note
2019.12.13 note Fast Transformer Decoding: One Write-Head is All You Need They have proposed an alternative to
2020-02-21 13:51:43
原创 2019.10.18 note
2019.10.18 note Quaternion Knowledge Graph Embeddings In this work, authors move beyond the traditional complex-val
2019-10-25 19:57:26
原创 2019.10.8 note
2019.10.8 note Commonsense Knowledge Base Completion This work proposes a task of complete commonsense knowledge ba
2019-10-25 19:57:16
原创 2019.10.12 note
2019.10.12 note Exploiting Explicit Paths for Multi-hop Reading Comprehension The task and proposed method for 2 ho
2019-10-25 19:57:16
原创 2019.9.5 note
2019.9.5 note A Structural Probe for Finding Syntax in Word Representations The probe identifies a linear transfor
2019-10-25 19:57:16
1
原创 2019.9.4 note
2019.9.4 note A Simple Theoretical Model of Importance for Summarization Define Redundancy, Relevance and Informa
2019-10-25 19:57:16