机器学习:概述.2
文/卡梅隆·伯科
日期
2020年1月21日
Machine learning (ML) is an emerging field that attracts a great amount of interest, 但并没有得到很好的理解. This blog post expands on the ideas discussed in the previously published blog post “机器学习:概述.1” which presents an overview of ML principles and applications in FAQ form. 在为泰党.2, 我们提供了为什么以及何时应该使用机器学习的见解, 机器学习算法是如何训练的, 以及AEC领域的潜在应用领域.
我为什么要使用机器学习?
The key benefit to considering ML is that it can be applied to a wide variety of problems. Applications can include basic tasks such as simple corporate activities, and highly complex tasks such as recognizing and predicting trends. 使用ML的任务示例包括:
- 员工招聘查看简历，筛选候选人.
- 财务状况:匹配发票的自然语言处理.
- 预见性维护: Predicting and detecting anomalies in infrastructure to prevent disruptions (e.g. 混凝土桥的状况).
- 产品推荐:使用购买记录向消费者推荐产品.
- 计算机视觉:识别和分类图像和视频中的对象.
什么时候应该使用ML?
何时使用ML的问题很复杂, as developing an ML solution requires significant investment in time and resources. In order to develop an ML solution that creates value, the following questions should be asked. 如果以下任何一个问题的答案是“否”, 机器学习不太可能产生显著的好处:
- Do you have a good understanding of the problem that must be solved?
- Is the problem you are trying to solve a recurring, repetitive problem? 这是一个可扩展和/或可转移的问题吗?
- Is ML expected to save a significant amount of time and/or resources?
- 是否有一个大的数据集来训练软件? If a dataset is not readily available, is it relatively easy to obtain an appropriate dataset?
如何“训练”机器学习软件?
An ML algorithm can be thought of as a person learning a new task. 起初, 一个人通过培训学习如何完成任务，然后, 通过执行任务, 这个人获得了经验. This experience gives the person the ability to complete more complex tasks, 更快速有效地完成任务. Similarly, an ML algorithm must be trained by giving it vast amounts of data. The ML algorithm then artificially “learns” how to complete the task, 这使得它能够“理解”如何完成类似的任务. The four primary methods of training an ML algorithm are as follows:
- 监督式学习: The algorithm is given inputs and the corresponding correct outputs (i.e. “带安全标签的数据”). The algorithm then calibrates itself based on its actual output and the correct given output. 例子:信用卡欺诈行为.
- Semi-supervised学习: The algorithm uses a mix of labeled data and unlabeled data for training (i.e. 正确输出和错误输出的混合), 算法必须找出“正确”的答案. 这通常用于获取标记数据的成本很高的情况. 示例:分类、回归和预测.
- 无监督学习: The algorithm is given unlabeled data and must recognize trends within the data by itself. 示例:产品推荐算法.
- 强化学习: Through trial and error, the algorithm learns which actions generate the optimal results. 例子:机器人、导航和电子游戏ai.
在使用机器学习之前我应该考虑什么?
Given a sound understanding of the required data and the problem that is to be solved using ML, 应考虑下列项目:
- The appropriate type of algorithm to be employed in order to solve the problem (regression, 决策树, 聚类, 等.).
- 要使用的算法训练类型. 这在很大程度上取决于可用的数据集, 以及使用的算法类型, 因为某些类型的算法需要更多的数据, 而另一些则需要非常高质量的数据(例如.e. 数据中没有异常值或“噪声”).
- The expected correlation between different parameters within the dataset and the expected output (i.e. after the ML algorithm is run, what do you think the relationship between the data will look like? Is this different than what you expected a human user would find using non-ML methods?)
如何在架构中应用机器学习, 工程, 和建筑(AEC)部门?
情报:
- General business operations: Hiring, finances, opportunity tracking.
- Transportation analytics: Transit routing, signal timings, delay/travel time predictions.
建筑:
- 智能建筑平台:能源使用预测, 供暖和照明自动化, 系统异常检测.
- 动态建筑围护结构设计:跟踪空气, 水, 热光, and noise transfer between a building’s internal environment and the external environment.
基础设施:
- 调查:数据收集、处理和分析.
- Identification of potential development sites: Property value prediction, 土地利用模式, 开发应用程序.
