Vision

David Marr

出版社

The MIT Press

出版时间

2010-07-08

ISBN

9780262514620

评分

★★★★★
书籍介绍

David Marr's posthumously published Vision (1982) influenced a generation of brain and cognitive scientists, inspiring many to enter the field. In Vision, Marr describes a general framework for understanding visual perception and touches on broader questions about how the brain and its functions can be studied and understood. Researchers from a range of brain and cognitive sciences have long valued Marr's creativity, intellectual power, and ability to integrate insights and data from neuroscience, psychology, and computation. This MIT Press edition makes Marr's influential work available to a new generation of students and scientists. In Marr's framework, the process of vision constructs a set of representations, starting from a description of the input image and culminating with a description of three-dimensional objects in the surrounding environment. A central theme, and one that has had far-reaching influence in both neuroscience and cognitive science, is the notion of different levels of analysis--in Marr's framework, the computational level, the algorithmic level, and the hardware implementation level. Now, thirty years later, the main problems that occupied Marr remain fundamental open problems in the study of perception. Vision provides inspiration for the continuing efforts to integrate knowledge from cognition and computation to understand vision and the brain.

AI导读
核心看点
  • 提出视觉计算的三层次理论框架
  • 系统阐述从图像到三维描述的过程
  • 奠定计算神经科学的理论基础
适合谁读
  • 计算机视觉与AI领域研究者
  • 认知科学与神经科学专业学生
  • 对视觉机制有深度探索兴趣者
读前提醒
  • 建议对照英文原版以克服翻译障碍
  • 需具备扎实的数学与逻辑基础
  • 重点理解计算理论与算法实现区别
读者共识
  • 学术地位极高,是领域内必读经典
  • 中文版翻译质量极差,严重影响阅读
  • 理论深刻抽象,入门门槛相对较高

本导读基于书籍简介、目录、原文摘录、短评和书评生成,不等同于全文精读。

精彩摘录
  • "if one chooses the Arabic numeral representation, it is easy to discover whether a number is a power of 10 but difficult to discover whether it is a power of 2. If one chooses the binary representation, the situation is reversed. Thus, there is a trade-off; any particular representation makes certai"
  • "Warrington已经触到了人类视觉的精华所在——人类视觉告诉我们的是形状、空间及空间位型。这就为阐明视觉的目的——从图像中建立物体的形状和位置的一个描述——铺平了道路。当然,这决不是视觉所能完成的全部工作;视觉还告诉我们构成物体的表面的照明情况和反射情况——表面的亮度、颜色和视觉质地——以及表面的运动情况等等。但这些看来都是次要的东西;在一个把求得形状表象作为视觉的主要任务的理论中,可以把这些次要的东西暂且放在一边"
  • "任何一种特殊的表象,一方面它使某些信息变得明确,但另一方面,作为一种代价,它又使另一些信息隐藏起来,而隐藏起来的信息可能是极难恢复的。 信息如何被表象,这个问题很重要。表象决定着什么信息被明确表达,因而也决定着什么信息被隐藏起来。"
  • "加法是一个映射,它把数对映成单个数。"
  • "从运动恢复结构"
  • "For if we are capable of knowing what is where in the world, our brains must somehow be capable of representing this information-in all its profusion of color and form, beauty motion, and detail. The study of vision must therefore include not only the study of how to extract from images the various "
  • "For the subject of vision, there is no single equation or view that explains everything. Each problem has to be addressed from several points of view-as a problem in representing information, as a computation capable of deriving that representation, and as a problem in the architecture of a computer"
  • "Vision is therefore, first and foremost, an information-processing task, but we cannot think of it just as a process. For if we are capable of knowing what is where in the world, our brains must somehow be capable of representing this information—in all its profusion of color and form, beauty, motio"
作者简介
David Courtnay Marr是计算神经科学领域的创始人之一,曾任麻省理工学院心理学教授。Shimon Ullman是位于以色列雷霍沃特的魏茨曼科学研究所的计算机科学Samy和Ruth Cohn讲席教授。Tomaso Poggio是麻省理工学院脑和认知科学系的Eugene McDermott讲席教授。Ullman和Poggio都曾在麻省理工学院与David Marr共事。 译者简介 吴佳俊,斯坦福大学计算机科学系助理教授,研究方向是计算机视觉、机器学习和计算认知科学。 加入斯坦福大学之前,曾是谷歌研究院的访问研究员,并分别在清华大学和麻省理工学院获得了学士和博士学位。 他的研究曾获ACM博士学位论文荣誉提名奖、AAAI/ACM SIGAI博士学位论文奖、麻省理工学院George M. Sprowls人工智能与决策博士学位论文奖,以及2020年三星人工智能年度研究人员奖。
目录
Detailed Contents
Foreword by Shimon Ullman xvii
Preface xxiii
PART I
INTRODUCTION AND

显示全部
用户评论
读了著名的第一章。相见恨晚,这本书应该是认知神经入门的必读书目啊。
不是计算机科学的,后面看不太懂,至少第一章是值得所有人看的。
在这个数据可以轻易获得的时代,Marr的three levels of analysis值得拿来反复咀嚼。
landmark
以客体理解主体,在造AI的过程中尝试理解人类(什么叫大棋)。虽然不认同Mind可以简化为数理逻辑建构:1. 人类思维本身的局限;2. 无意识/直觉/联觉/直观可能没法“算”出来,至少没法走流程“算”出来。也许在20世纪,把大脑类比成信息处理系统是自然而然的事。21世纪能不能把集体意识类比成互联网呢。未来说不定还能类比成时光机呢。毕竟人类只能靠自己的心智来理解自己。
Good research should be like this. It envisioned and established a field that would prosper 30 years later. Research is for the next generation, not only for today.
2022.3在读。用deepl翻译艰难阅读中。。有些认知科学和生物学知识
真牛逼!!! 秒杀所有turing奖获得者!
被设问体系吸住,又同时被解构结构压制。要重啃,再重啃。
经典
下载
收藏