### 机器学习代写|自然语言处理代写NLP代考|CS11-711

statistics-lab™ 为您的留学生涯保驾护航 在代写自然语言处理NLP方面已经树立了自己的口碑, 保证靠谱, 高质且原创的统计Statistics代写服务。我们的专家在代写自然语言处理NLP代写方面经验极为丰富，各种代写自然语言处理NLP相关的作业也就用不着说。

• Statistical Inference 统计推断
• Statistical Computing 统计计算
• Advanced Probability Theory 高等概率论
• Advanced Mathematical Statistics 高等数理统计学
• (Generalized) Linear Models 广义线性模型
• Statistical Machine Learning 统计机器学习
• Longitudinal Data Analysis 纵向数据分析
• Foundations of Data Science 数据科学基础

## 机器学习代写|自然语言处理代写NLP代考|Input embedding

The input embedding sub-layer converts the input tokens to vectors of dimension $d_{\text {modd }}=512$ using learned embeddings in the original Transformer model. The structure of the input embedding is classical:

The embedding sub-layer works like other standard transduction models. A tokenizer will transform a sentence into tokens. Each tokenizer has its methods, but the results are similar. For example, a tokenizer applied to the sequence “the Transformer is an innovative NLP model!” will produce the following tokens in one type of model:You will notice that this tokenizer normalized the string to lower case and truncated it into subparts. A tokenizer will generally provide an integer representation that will be used for the embedding process. For example:

There is not enough information in the tokenized text at this point to go further. The tokenized text must be embedded.
The Transformer contains a learned embedding sub-layer. Many embedding methods can be applied to the tokenized input.
I chose the skip-gram architecture of the word2vec embedding approach Google made available in 2013 to illustrate the embedding sublayer of the Transformer. A skip-gram will focus on a center word in a window of words and predicts context words. For example, if word(i) is the center word in a two-step window, a skipgram model will analyze word(i-2), word(i-1), word(i+1), and word(i+2). Then the window will slide and repeat the process. A skip-gram model generally contains an input layer, weights, a hidden layer, and an output containing the word cmbeddings of the tokenized input words.
Suppose we need to perform embedding for the following sentence:
The black cat sat on the couch and the brown dog slept on the rug.
We will focus on two words, black and brown. The word embedding vectors of these two words should be similar.
Since we must produce a vector of size $d_{\text {madel }}=512$ for each word, we will obtain a size 512 vector embedding for each word:The word black is now represented by 512 dimensions. Other embedding methods could be used and $d_{\text {mudel }}$ could have a higher number of dimensions.

## 机器学习代写|自然语言处理代写NLP代考|Positional encoding

We enter this positional encoding function of the Transformer with no idea of the position of a word in a sequence:

We cannot create independent positional vectors that would have a high cost on the training speed of the Transformer and make attention sub-layers very complex to work with. The idea is to add a positional encoding value to the input embedding instead of having additional vectors to describe the position of a token in a sequence.
We also know that the Transformer expects a fixed size $d_{\text {madel }}=512$ (or other constant value for the model) for each vector of the output of the positional encoding function.
If we go back to the sentence we used in the word embedding sub-layer, we can see that black and brown may be similar, but they are far apart:
The black cat sat on the couch and the brown dog slept on the rug.
The word black is in position 2, pos $=2$, and the word brown is in position 10 , pos $=10$.
Our problem is to find a way to add a value to the word embedding of each word so that it has that information. However, we need to add a value to the $d_{\text {madel }}=512$ dimensions! For each word embedding vector, we need to find a way to provide information to $i$ in the range $(\theta, 512)$ dimensions of the word embedding vector of black and brown.

There are many ways to achieve this goal. The designers found a clever way to use a unit sphere to represent positional encoding with sine and cosine values that will thus remain small but very useful.

## 机器学习代写|自然语言处理代写NLP代考|Input embedding

Transformer 包含一个学习的嵌入子层。许多嵌入方法可以应用于标记化输入。

## 机器学习代写|自然语言处理代写NLP代考|Positional encoding

black 这个词在位置 2，pos=2, 单词 brown 在位置 10 , pos=10.

## 有限元方法代写

tatistics-lab作为专业的留学生服务机构，多年来已为美国、英国、加拿大、澳洲等留学热门地的学生提供专业的学术服务，包括但不限于Essay代写，Assignment代写，Dissertation代写，Report代写，小组作业代写，Proposal代写，Paper代写，Presentation代写，计算机作业代写，论文修改和润色，网课代做，exam代考等等。写作范围涵盖高中，本科，研究生等海外留学全阶段，辐射金融，经济学，会计学，审计学，管理学等全球99%专业科目。写作团队既有专业英语母语作者，也有海外名校硕博留学生，每位写作老师都拥有过硬的语言能力，专业的学科背景和学术写作经验。我们承诺100%原创，100%专业，100%准时，100%满意。

## MATLAB代写

MATLAB 是一种用于技术计算的高性能语言。它将计算、可视化和编程集成在一个易于使用的环境中，其中问题和解决方案以熟悉的数学符号表示。典型用途包括：数学和计算算法开发建模、仿真和原型制作数据分析、探索和可视化科学和工程图形应用程序开发，包括图形用户界面构建MATLAB 是一个交互式系统，其基本数据元素是一个不需要维度的数组。这使您可以解决许多技术计算问题，尤其是那些具有矩阵和向量公式的问题，而只需用 C 或 Fortran 等标量非交互式语言编写程序所需的时间的一小部分。MATLAB 名称代表矩阵实验室。MATLAB 最初的编写目的是提供对由 LINPACK 和 EISPACK 项目开发的矩阵软件的轻松访问，这两个项目共同代表了矩阵计算软件的最新技术。MATLAB 经过多年的发展，得到了许多用户的投入。在大学环境中，它是数学、工程和科学入门和高级课程的标准教学工具。在工业领域，MATLAB 是高效研究、开发和分析的首选工具。MATLAB 具有一系列称为工具箱的特定于应用程序的解决方案。对于大多数 MATLAB 用户来说非常重要，工具箱允许您学习应用专业技术。工具箱是 MATLAB 函数（M 文件）的综合集合，可扩展 MATLAB 环境以解决特定类别的问题。可用工具箱的领域包括信号处理、控制系统、神经网络、模糊逻辑、小波、仿真等。