2019-02-02 Week 5
Shares From Internet
- AWS Activating TensorFlow
- Comprehensive Python Cheatsheet
- GAN by Example using Keras on Tensorflow Backend
- How to Implement the Conv1DTranspose in keras?
- Advanced-Deep-Learning-with-Keras
- 人人都能看懂的LSTM
- Step-by-step to LSTM: 解析LSTM神经网络设计原理
- What's causing the vanishing gradient problem? Unstable gradients in deep neural …
leetcode 312. Burst Balloons
题目大意 给定n个气球,每个气球有一个数字,用数组nums来表示n个气球上面的数字。如果气球i被打破,那么你会得到nums[left] * nums[i] * nums[right].这里left和right分别为气球i的左右两边的气球。打破所有的气球后把所有的数字相加,求解怎么打破这些气球使得最后得到的数字最大。
leetcode 321. Create Maximum Number
题目大意 给定长度为m和n的两个数组,数组里面数字为0到9.要求从这两个数组里面去k个数字构成的数字的最大值。k<=m+n。题目要求新的数字的顺序跟原来数组的数字顺序保持一致。
leetcode 322. Coin Change
题目大意 给定一堆硬币和一个数字,求组成那个数字的最少硬币个数。如果币值没法构成给定数字,返回 -1
leetcode 377. Combination Sum IV
题目大意 给定一个整型数组,里面没有重复数字。求解所有可能的组合使得组合的和为给定的整数。
leetcode 416. Partition Equal Subset Sum
题目大意 给定一个数组,求能不能把数组分成两部分使得两个子数组的和相等
Credit Card Fraud Detection / Imbalanced data modeling - Part III: Ensembling/Stacking models
It is important that credit card companies are able to recognize fraudulent credit card transactions so that customers are not charged for items that they did not purchase. This dataset presents transactions that occurred in two days, where we have 492 frauds out of 284,807 transactions. The dataset is highly unbalanced.
Credit Card Fraud Detection / Imbalanced data modeling - Part II: Random Forest
It is important that credit card companies are able to recognize fraudulent credit card transactions so that customers are not charged for items that they did not purchase. This dataset presents transactions that occurred in two days, where we have 492 frauds out of 284,807 transactions. The dataset is highly unbalanced.
Credit Card Fraud Detection / Imbalanced data modeling - Part I: Logistic Regression
It is important that credit card companies are able to recognize fraudulent credit card transactions so that customers are not charged for items that they did not purchase. This dataset presents transactions that occurred in two days, where we have 492 frauds out of 284,807 transactions. The dataset is highly unbalanced.