- Deep Learning Essentials
- Wei Di Anurag Bhardwaj Jianing Wei
- 296字
- 2021-06-30 19:17:46
Data representation
In this section, we will look at core data structures and representations used most commonly across different linear algebra tasks. This is not meant to be a comprehensive list at all but only serves to highlight some of the prominent representations useful for understanding deep learning concepts:
- Vectors: One of the most fundamental representations in linear algebra is a vector. A vector can be defined as an array of objects, or more specifically an array of numbers that preserves the ordering of the numbers. Each number can be accessed in a vector based on its indexed location. For example, consider a vector x containing seven days a week encoded from 1 to 7, where 1 represents Sunday and 7 represents Saturday. Using this notation, a particular day of the week, say Wednesday, can be directly accessed from the vector as x [4]:

- Matrices: These are a two-dimensional representation of numbers, or basically a vector of vectors. Each matrix, m, is composed of a certain number of rows, r, and a specified number of columns, c. Each of i rows, where 1 <= i <= r, is a vector of c numbers. Each of the j columns, where 1 <=j <= c, is also a vector of r numbers. Matrices are a particularly useful representation when we are working with images. Though real-world images are three-dimensional in nature, most of the computer vision problems are focused on the two-dimensional presentation of images. As such, a matrix representation is an intuitive representation of images:

- Identity matrices: An identity matrix is defined as a matrix which, when multiplied with a vector, does not change the vector. Typically, an identity matrix has all elements as 0 except on its main diagonal, which is all 1s:

推薦閱讀
- 樂高機(jī)器人EV3設(shè)計(jì)指南:創(chuàng)造者的搭建邏輯
- Photoshop CS4經(jīng)典380例
- 教父母學(xué)會(huì)上網(wǎng)
- TIBCO Spotfire:A Comprehensive Primer(Second Edition)
- 21天學(xué)通C++
- DevOps:Continuous Delivery,Integration,and Deployment with DevOps
- 悟透AutoCAD 2009案例自學(xué)手冊(cè)
- 精通LabVIEW程序設(shè)計(jì)
- Puppet 3 Beginner’s Guide
- 單片機(jī)C51應(yīng)用技術(shù)
- 微機(jī)組裝與維護(hù)教程
- ARM嵌入式系統(tǒng)開發(fā)完全入門與主流實(shí)踐
- 多媒體技術(shù)應(yīng)用教程
- Outlook時(shí)間管理秘笈
- Orange'S:一個(gè)操作系統(tǒng)的實(shí)現(xiàn)