Hal Daume III wrote a great piece about this issue. Here's an excerpt:
[...] There are lots of ways to be better than such a baseline, and so "beating" it does not teach me anything. I always tell students not to get too pleased when they get state of the art performance on some standard task: someone else will beat them next year. If the only thing that I learn from their papers is that they win on task X, then next year there's nothing to learn from that paper. The paper has to teach me something else to have any sort of lasting effect: what is the generalizable knowledge.
The point is that an evaluation is not an end in itself. An evaluation is there to teach you something, or to substantiate something that I want to teach you. If I want to show you that X is important, then I should show you an experiment that isolates X to the best of my ability and demonstrates an improvement, preferably also with an error analysis that shows that what I claim my widget is doing is actually what it's doing.
To deep learning researchers: Stop throwing all the tricks in the book to push your numbers up (ie dropout, sophisticated optimizers, fancy parameter initialization, dataset augmentation). If you need these tricks to prove your point, then I'm sorry to say you don't have one. Your results are meaningless since you've confounded it with so many other things. Instead of spending so much effort pushing your method to state-of-the-art performance, how about spending some time simplifying it. Show that the intuitions you had for your idea is in fact what's happening. Coming from someone on the application side, if your idea isn't simple to implement or intuitive, no one will use it
Occam's razor has so much truth in this field. There are too many times where I reproduce a result only to find it only works exactly in the conditions described in the paper. This is a great way to waste another person's time.
....In other words, I just want to stop reading crappy papers........
分享到:
相关推荐
企业动力模型规范(Business Motivation Model Specification)是由对象管理组织(Object Management Group,简称OMG)制定的标准文档,用于详细说明企业动力模型(Business Motivation Model,简称BMM)。...
### 商业动机模型(Business Motivation Model, BMM) #### 概述 商业动机模型(Business Motivation Model,简称BMM)是一种结构化的框架,用于描述企业的战略目标、动机以及如何实现这些目标的方法。该模型由业务...
《传统课堂与在线学习课程中学生动机的比较分析》这篇论文深入探讨了在传统课堂教学与电子学习课程中,学生动力的差异。通过多元方差分析(Multivariate analysis of variance),研究者Rovai、Ponton、Wighting、...
《A Theory of Human Motivation》是心理学家亚伯拉罕·马斯洛(Abraham H. Maslow)提出的一个著名理论,通常被称为“马斯洛需求层次理论”。这个理论是心理学领域的重要里程碑,对理解人类行为、管理学、教育学等多...
Self-determination theory posits that the degree to which a prosocial act is volitional or ... Four studies tested the impact of autonomous and controlled motivation for helping others on well-b
We believe that the Social ... In this chapter we illustrate the motivation and some solutions being adopted by the innovators involved in quantitative social science studies of individual behaviour
It discusses cutting-edge research at the intersection between different fields, from topics such as cognition and behavior, motivation and emotions, to neurocomputing, deep learning, classification ...
01 Motivation, Standardization, Acceptance
A multidimensional motivation instrument A MULTIDIMENSIONAL MOTIVATION INSTRUMENT MARGARET E. UGUR0GI.U Cenier for Educarional Developmen:. Universiry of Illinois a: :he Medical Cen:er DIANE ...
Motivation管理学英文版.pptx
"Motivation and Values" 这份PPT聚焦于消费者的动力机制和价值观,这对于理解消费者行为至关重要。 动机(Motivation)是驱动人们行为的内在力量,指的是引发人们采取特定行动的那些过程。当需求被唤醒时,人们会...
标题"MOTIVATION FOREX BOOK_surfacec4v_finance_TheRisk_forex_motivation"揭示了这个压缩包文件的核心主题,主要围绕外汇交易(Forex)领域的动力与风险。这是一份专门探讨如何在外汇市场中成功并管理风险的资料,...
名称:Daily Motivation(励志名言) ---------------------------------------- 版本:2.4.13 作者:https://atagowani.com/ 分类:商业购物 ---------------------------------------- 概述:以动力开始每一项搜索。...
本文档“1101 QA motivation.doc”似乎探讨了与QA团队成员激励相关的主题,尤其是在一个考试或评估的上下文中。文档提到了员工对工作的期望以及上司与下属对这些激励因素的不同看法,这有助于我们理解如何有效激发QA...
JavaServer Pages(JSP)是Java平台上用于构建动态web应用程序的一种技术。...JSP的动机和历史背景,以及其工作原理,是理解这项技术核心的三个关键方面。 首先,我们来看一下JSP的动机。在JSP诞生之前,Web开发者通常...
开始每一个搜索的动机。每当您打开一个新标签时,这个扩展就会给您一个动机。 用动力开始每一个新的搜索! 每次您打开新标签页时...**对于书呆子:https://github.com/AtaGowani/Daily-Motivation ** 支持语言:English
总结起来,"particles motivation"项目展示了如何结合粒子系统、OpenGL和CUDA,利用GPU的并行计算能力实现实时的粒子碰撞模拟,并提供交互式的用户体验。这不仅是对计算机图形学技术的实践,也是对高性能计算领域的...
Motivation: A structure-process interpretation MOTIVATION : A STRUCTURE-PROCESS INTERPRETATION ...empirical research in motivation has been conducted by psychologists who were concerned with observ
「WEB应用防火墙」Effective Leadership and Motivation What It Took to Race around the World - 信息安全 数据分析 安全研究 无线安全 安全漏洞 终端安全