LeetCode ZigZag Conversion

Description

The string “PAYPALISHIRING” is written in a zigzag pattern on a given number of rows like this: (you may want to display this pattern in a fixed font for better legibility)

P A H N
A P L S I I G
Y I R
And then read line by line: “PAHNAPLSIIGYIR”
Write the code that will take a string and make this conversion given a number of rows:

string convert(string text, int nRows);
convert(“PAYPALISHIRING”, 3) should return “PAHNAPLSIIGYIR”.

The original problem is here:

Read More

LeetCode Add Two Numbers

Description

You are given two linked lists representing two non-negative numbers. The digits are stored in reverse order and each of their nodes contain a single digit. Add the two numbers and return it as a linked list.

Input: (2 -> 4 -> 3) + (5 -> 6 -> 4)
Output: 7 -> 0 -> 8

The original problem is here:

Read More

LeetCode Two Sum

Description

Given an array of integers, find two numbers such that they add up to a specific target number.

The function twoSum should return indices of the two numbers such that they add up to the target, where index1 must be less than index2. Please note that your returned answers (both index1 and index2) are not zero-based.

You may assume that each input would have exactly one solution.

Input: numbers={2, 7, 11, 15}, target=9
Output: index1=1, index2=2

The original problem is here:

Read More

感知机

简介

1957年Rosenblatt提出感知机(perceptron),成为神经网络和支持向量机的基础。感知机是二类分类的线性分类模型,输入是实例的特征向量,输出是实例的类别。感知机学习的目标是求出将训练数据进行线性划分的分离超平面,感知机属于判别模型。

Read More

机器学习概述

简介

机器学习就是将数据转变成信息。机器学习一般采用统计方法,由数据驱动,从数据中提取特征、抽象出模型、发现数据中的知识,最终应用到数据的分析和预测。

统计学习是关于计算机基于数据构建概率统计模型并运用模型对数据进行预测与分析的一门学科。

Read More

Paper Reading:《TTS Synthesis with Bidirectional LSTM based Recurrent Neural Networks》

论文信息

简介

采用双向LSTM单元的RNN能够捕捉参数式语音合成中一个语音句子中的任意两时刻的相关性。

Read More

Paper Reading: 《DEEP MIXTURE DENSITY NETWORKS FOR ACOUSTIC MODELING IN STATISTICAL PARAMETRIC SPEECH SYNTHESIS》

论文信息

简介

利用深层神经网络(DNNs)的参数语音合成(SPSS),被证明具有生成自然的合成语音的能力。然而,语音合成中基于DNN的声学建模还有不足之处,例如目标函数是单峰的、缺少预测方差的能力。
为了解决这些局限,本文研究了利用混合密度的输出层,它能够在给定输入特征条件下,估计输出特征的全概率密度函数。实验的客观和主观结果表明利用混合密度输出层提高了预测的声学特征的准确性、以及合成语音的自然度。

Read More

Paper Reading:《STATISTICAL PARAMETRIC SPEECH SYNTHESIS USING DEEP NEURAL NETWORKS》

论文信息

简介

利用深层神经网络(Deep Neural Network,DNN)取代基于隐马尔科夫模型(Hidden Markov Models,HMMs)的语音合成中的决策树聚类和高斯混合模型(Guassian Mixture Models, GMMs),以提高声学建模的准确性。

Read More