- 博客(182)
- 资源 (2)
- 收藏
- 关注
RSS订阅原创 2020.1.13 note
2020.1.13 noteAdderNet: Do We Really Need Multiplications in Deep Learning?Compared with cheap addition operation, multiplication operation is of much higher computation complexity. The widely-used ...
2020-01-15 12:23:47
4458
原创 2019.12.17 note
2019.12.17 noteFilter Response Normalization Layer: Eliminating Batch Dependence in the Training of Deep Neural NetworksBatch Normalization (BN) is a highly successful and widely used batch dependen...
2019-12-17 15:19:32
817
原创 2019.12.13 note
2019.12.13 noteFast Transformer Decoding: One Write-Head is All You NeedThey have proposed an alternative to multi-head attention - multi-query attention, with much lower memory bandwidth requir...
2019-12-12 10:33:24
1058
原创 2019.11.15 note (2)
2019.11.15 note (2)Intriguing properties of neural networksDeepFool: a simple and accurate method to fool deep neural networksTowards Evaluating the Robustness of Neural NetworksDISTRIBUTIO...
2019-11-14 21:43:25
797
2
原创 2019.11.15 note (1)
2019.11.15 note (1)EXPLAINING AND HARNESSING ADVERSARIAL EXAMPLESFGSM (Fast Gradient Sign Method)Adversarial examples in the physical worldAnother version:Towards Deep Learning Models Resi...
2019-11-13 22:46:47
717
原创 2019.11.6 note
2019.11.5 noteDeepGCNs: Making GCNs Go as Deep as CNNsGraph Convolutional Networks (GCNs) offer an alternative that allows for non-Eucledian data as input to a neural network similar to CNNs. While ...
2019-11-07 10:25:03
1007
原创 2019.11.5 note
paper/2019.11.5 noteExploring the Limits of Transfer Learning with a Unified Text-to-Text TransformerThey propose a framework to cast every task they consider as a unified task: feeding the model t...
2019-11-05 15:01:32
956
原创 2019.10.18 note
2019.10.18 noteQuaternion Knowledge Graph EmbeddingsIn this work, authors move beyond the traditional complex-valued representations, introducing more expressive hypercomplex representations to mode...
2019-10-21 10:32:35
2368
原创 2019.9.6 note
2019.9.6 noteMeta-Learning with Implicit GradientsSimilar to paper darts, this work formulates Meta-learning as a two-level (inner/outer) optimization problem. To make the meta-learning process mode...
2019-10-16 22:55:20
760
原创 2019.10.12 note
2019.10.12 noteExploiting Explicit Paths for Multi-hop Reading ComprehensionThe task and proposed method for 2 hops:(a) Find a passage p1p_1p1 that contains a head entity heh_ehe from the questi...
2019-10-16 21:30:05
712
原创 2019.10.8 note
2019.10.8 noteCommonsense Knowledge Base CompletionThis work proposes a task of complete commonsense knowledge base (generating new reasonable triplets in the knowledge base). This work also propose...
2019-10-16 21:25:43
1257
原创 2019.9.5 note
2019.9.5 noteA Structural Probe for Finding Syntax in Word RepresentationsThe probe identifies a linear transformation under which squared L2 distance encodes the distance between words in the pars...
2019-10-16 21:20:53
3527
1
原创 2019.9.4 note
paper/2019.9.4 notepaper/2019.9.4 noteA Simple Theoretical Model of Importance for SummarizationLogicENN: A Neural Based Knowledge Graphs Embedding Model with Logical RulesNorm-PreservationSqueeze-and...
2019-10-16 21:11:12
820
原创 变分法的一些例子
变分法的一些例子目录变分法的一些例子泛函变分法拉格朗日乘子法最大熵理论力学的哈密顿原理几何光学的费马原理几何和测地线黎曼几何和球面几何泛函函数到数的映射就是泛函，考虑一维情形的泛函I[y]=∫abF(x,y,y˙)dxI[y]=\int_a^b F(x, y, \dot y) dxI[y]=∫abF(x,y,y˙)dx其中I[y]I[y]I[y]表示映射函数y(x)y(x)y(x)到...
2019-03-30 12:06:48
6054
原创 张量求导
张量求导之前遇到的很多张量求导和算子运算的问题，我都采用形状法则不断尝试，或者展开成分量进行运算，这几天接触到了 Kronecker delta（δ\deltaδ） 和 Levi-Civita（ϵ\epsilonϵ）记号。终于给出了一个统一的张量求导运算框架，做个读书笔记。约定如果没有特殊声明，a,b,ca,b,ca,b,c 表示标量，x,y,zx, y, zx,y,z 表示向量，大写字母表...
2019-03-01 15:58:06
7596
原创 量子力学入门note
量子力学入门note因为高年级以后没什么算法课程了，所以这个博客也不怎么发算法解题报告了。读科研论文又没有什么阅读笔记的习惯，所以这个博客已经好久没有更新了。最近突然很好奇量子力学到底是什么，所以找了一本书看了一些很入门的东西。因为是入门的，所以不太涉及复杂的算子演算，PDE和函数空间的代数结构。仅仅用来满足一下我自己好奇心，在没有很深刻的数学工具的情况下做一点点了解和演算。物质波函数类比经...
2019-03-01 09:42:31
4769
空空如也
TA创建的收藏夹 TA关注的收藏夹
TA关注的人