上一页 1 ··· 168 169 170 171 172 173 174 175 176 ··· 273 下一页
摘要: Give a string s, count the number of non-empty (contiguous) substrings that have the same number of 0's and 1's, and all the 0's and all the 1's in th 阅读全文
posted @ 2018-03-18 22:22 bonelee 阅读(242) 评论(0) 推荐(0)
摘要: X is a good number if after rotating each digit individually by 180 degrees, we get a valid number that is different from X. Each digit must be rotate 阅读全文
posted @ 2018-03-17 23:44 bonelee 阅读(531) 评论(0) 推荐(0)
摘要: Calculate the sum of two integers a and b, but you are not allowed to use the operator + and -. Example: Given a = 1 and b = 2, return 3. 只能位运算: 0x011 阅读全文
posted @ 2018-03-17 22:17 bonelee 阅读(348) 评论(0) 推荐(0)
摘要: Given an array of integers where 1 ≤ a[i] ≤ n (n = size of array), some elements appear twice and others appear once. Find all the elements of [1, n] 阅读全文
posted @ 2018-03-17 12:49 bonelee 阅读(190) 评论(0) 推荐(0)
摘要: Given an array nums, write a function to move all 0's to the end of it while maintaining the relative order of the non-zero elements. For example, giv 阅读全文
posted @ 2018-03-17 09:19 bonelee 阅读(162) 评论(0) 推荐(0)
摘要: Given a non-empty 2D array grid of 0's and 1's, an island is a group of 1's (representing land) connected 4-directionally (horizontal or vertical.) Yo 阅读全文
posted @ 2018-03-17 00:47 bonelee 阅读(211) 评论(0) 推荐(0)
摘要: from:https://stackoverflow.com/questions/41616292/how-to-load-and-retrain-tflean-model This is to create a graph and save it To reload and retrain or 阅读全文
posted @ 2018-03-16 15:32 bonelee 阅读(4343) 评论(0) 推荐(1)
摘要: 理解dropout from:http://blog.csdn.net/stdcoutzyx/article/details/49022443 http://www.cnblogs.com/tornadomeet/p/3258122.html 开篇明义,dropout是指在深度学习网络的训练过程中, 阅读全文
posted @ 2018-03-16 15:05 bonelee 阅读(760) 评论(1) 推荐(0)
摘要: 正则化方法:L1和L2 regularization 本文是《Neural networks and deep learning》概览 中第三章的一部分,讲机器学习/深度学习算法中常用的正则化方法。(本文会不断补充) 正则化方法:防止过拟合,提高泛化能力 在训练数据不够多时,或者overtraini 阅读全文
posted @ 2018-03-16 10:25 bonelee 阅读(5462) 评论(0) 推荐(0)
摘要: 学习率如何影响训练? from:https://www.jiqizhixin.com/articles/2017-11-17-2 深度学习模型通常由随机梯度下降算法进行训练。随机梯度下降算法有许多变形:例如 Adam、RMSProp、Adagrad 等等。这些算法都需要你设置学习率。学习率决定了在一 阅读全文
posted @ 2018-03-16 09:33 bonelee 阅读(4710) 评论(0) 推荐(0)
上一页 1 ··· 168 169 170 171 172 173 174 175 176 ··· 273 下一页