自定义博客皮肤VIP专享

*博客头图:

格式为PNG、JPG,宽度*高度大于1920*100像素,不超过2MB,主视觉建议放在右侧,请参照线上博客头图

请上传大于1920*100像素的图片!

博客底图:

图片格式为PNG、JPG,不超过1MB,可上下左右平铺至整个背景

栏目图:

图片格式为PNG、JPG,图片宽度*高度为300*38像素,不超过0.5MB

主标题颜色:

RGB颜色,例如:#AFAFAF

Hover:

RGB颜色,例如:#AFAFAF

副标题颜色:

RGB颜色,例如:#AFAFAF

自定义博客皮肤

-+

Steve Wang's blog

点滴积累,点滴成长。

  • 博客(14)
  • 问答 (2)
  • 收藏
  • 关注

原创 日语动词变形总结

整理自《新版中日交流标准日本语》(第二版),部分变形记法参照新东方唐盾,因为盾盾桑的记法更容易记忆。目录序号标日语法术语学校语法术语1基本形终止形,连体形2ます形未然形+助动词“ます”3て形连用形+接续助词“て”4ない形未然形+助动词“ない”5た形连用形+助动词“た”6意志形未然形+助动词“う/よう”7ば形...

2019-01-30 16:00:38 14795

原创 序列模型第二周作业2:Emojify!

来自吴恩达深度学习系列视频:序列模型第二周作业2:Emojify!。如果英文对你来说有困难,可以参照:【中文】【吴恩达课后编程作业】Course 5 - 序列模型 - 第二周作业 - 词向量的运算与Emoji生成器,参照对英文的翻译并不能说完全准确,请注意这点。完整的ipynb文件参见博主github:https://github.com/Hongze-Wang/Deep-Learning-...

2019-01-20 11:34:06 853

原创 序列模型第二周作业1:Operations on word vectors

来自吴恩达深度学习系列视频:序列模型第二周作业1:Operations on word vectors。如果英文对你来说有困难,可以参照:【中文】【吴恩达课后编程作业】Course 5 - 序列模型 - 第二周作业 - 词向量的运算与Emoji生成器,参照对英文的翻译并不能说完全准确,请注意这点。完整的ipynb文件参见博主github:https://github.com/Hongze-W...

2019-01-19 21:03:37 688

原创 序列模型第一周作业3: Improvise a Jazz Solo with an LSTM Network

Improvise a Jazz Solo with an LSTM NetworkWelcome to your final programming assignment of this week! In this notebook, you will implement a model that uses an LSTM to generate music. You will even be...

2019-01-18 10:51:57 852

原创 序列模型第一周作业2: Character level language model - Dinosaurus land

Character level language model - Dinosaurus landWelcome to Dinosaurus Island! 65 million years ago, dinosaurs existed, and in this assignment they are back. You are in charge of a special task. Leadi...

2019-01-17 21:12:33 1337

原创 序列模型第一周作业1: Building your Recurrent Neural Network - Step by Step

Building your Recurrent Neural Network - Step by StepWelcome to Course 5’s first assignment! In this assignment, you will implement your first Recurrent Neural Network in numpy.Recurrent Neural Netw...

2019-01-17 16:54:14 740

原创 Bidirectional RNN (BRNN)

整理并翻译自吴恩达深度学习系列视频:序列模型第一周,有所详略。Bidirectional RNN (BRNN)Prerequisite:Gated Recurrent Unit(GRU)Long Short term memory unit(LSTM)

2019-01-17 09:42:16 4649

原创 Long Short term memory unit(LSTM)

整理并翻译自吴恩达深度学习系列视频:序列模型第一周。Prerequisite:Gated Recurrent Unit(GRU)Long Short term memory unit(LSTM)GRU 和 LST的对比。LTSM计算公式如下:C~<t>=tanh(Wc[C<t−1>,x<t>]+bc...

2019-01-16 22:14:55 702

原创 Gated Recurrent Unit(GRU)

整理并翻译自吴恩达深度学习系列视频:序列模型第一周,有所详略。Gated Recurrent Unit(GRU)Gated Recurrent Unit(GRU), which is a modification to the RNN hidden layer that makes it much better at capturing long range connections an...

2019-01-16 21:52:34 3421

原创 循环神经网络模型

整理并翻译自吴恩达深度学习系列视频:序列模型第一周,有所详略。Recurrent Neural Network一个标准的循环神经网络如图所示,在网络的每一个时间步ttt,它接受前一层的激活函数值a<t−1>a^{<t-1>}a<t−1>和输入x

2019-01-16 20:35:13 897

原创 Bellman-Ford algorithm

Bellman-Ford algorithmBellman-Ford algorithm用于在有负权值的图上求最短路径,是动态规划的一个应用,所以你需要阅读之前的一片介绍动态规划的博文Dynamic Programming,抱歉,期末复习中,没有空闲翻译成中文。Pseudocoded[s] <- 0for each v ∈ V-{s} do d[v] <- ∞f...

2019-01-11 14:47:45 357

原创 Dynamic Programming

Compare to Greedy and Divide_and_conquerGreedy.Build up a solution incrementally, myopically optimizing some local criterion.Divide-and-conquer.Break up a problem into sub-problem into sub-problem...

2019-01-10 21:36:02 702

原创 Divide and Conquer

Divide and Conquer: OverviewDivide and conquerBreak up problem into several partsSolve each part recursivelyCombine solutions to sub-problems into overall solutionMost common usageBreak up pr...

2019-01-10 21:23:41 379

原创 Greedy Analysis Strategies

Greedy Analysis StrategiesGreedy algorithm stays ahead.Show that after each step of the greedy algorithm, its solution is at least as good as other algorithm’s.Ex.Interval schedulingStructural...

2019-01-10 13:28:00 425

空空如也

TA创建的收藏夹 TA关注的收藏夹

TA关注的人

提示
确定要删除当前文章?
取消 删除