machine learning key word (part one)

本文介绍了机器学习领域的核心术语,包括学习算法、实例/样本、样例、标记等,并详细解释了监督学习、无监督学习、分类、回归等概念,为初学者提供了全面的基础知识。

摘要生成于 C知道 ,由 DeepSeek-R1 满血版支持, 前往体验 >

machine learning:机器学习常用术语(one part)

    learning algorithm:学习算法

    instance/sample:示例/样本

    example:样例

    label:标记

    attribute/feature:属性/特征

    attribute value:属性值

    attribute space:属性空间

    sample space:样本空间/输入空间

    feature vector:特征向量

    dimensionality:维数

    hypothesis:假设

    ground-truth:真相、真实

    learner:学习器

    training data:训练数据

    training sample:训练样本

    test sample:测试样本

    training set:训练集

    label space:标记空间、输出空间

    classification:分类

    regression:回归

    binary classification:二分类

    multi-class classification:多分类

    positive class:正类

    negative class:反类

    clustering:聚类

    supervised learning:监督学习

    unsupervised learning:无监督学习

    generalization:泛化

    distribution:分布

    independent and identically distributed:独立同分布(i,i,d.)

    induction:归纳

    inductive learning:归纳学习

    deduction:演绎

    specialization:特化

    version space:版本空间

    fit:匹配

    inductive bias:归纳偏好(简称“偏好”)

    Occam's razor

    No Free Lunch Theorem:没有免费的午餐定量(简称“NFL”)

    artificial intelligence:人工智能

    General Problem Solving:通用问题求解

    Logic Theorist:逻辑理论家

    connectionism:连接主义

    symbolism:符号主义

    perceptron:感知机

    Inductive Logic Programming:归纳逻辑程序设计(简称“ILP”)

    statistical learning:统计学习

    support vector meachine:支持向量机(简称“SVM”)

    kernel methods:核方法

    data mining:数据挖掘

    crowdsourcing:众包

    transfer learning:迁移学习

    learning by analogy:类比学习

    deep learning:深度学习
### CS Project 5 Machine Learning Course Materials and Requirements For a graduate-level machine learning course project, specific prerequisites include prior knowledge from either a computer vision or machine learning course[^1]. The focus on these areas ensures that students have foundational understanding necessary for advanced topics. In terms of mathematical preparation, several key skills are essential for success in such projects. These encompass linear algebra, calculus, probability theory, statistics, optimization techniques, and algorithmic thinking[^2]. To gain deeper insights into deep learning methodologies relevant to this type of coursework, resources exist which provide both theoretical explanations as well as practical implementations using frameworks like Keras. For instance, there is an introductory guide available through video tutorials titled "Neural Networks Demystified," created by Stephen Welch, alongside interactive guides covering basics visually presented by J Alammar[^3]. Given the context provided about predicting qualified candidates based on test scores, it can be inferred that part of the project may involve applying statistical models or machine learning algorithms to analyze data sets related to candidate evaluation metrics[^4]. #### Example Code Snippet Demonstrating Basic Data Analysis Using Python Pandas Library ```python import pandas as pd # Load dataset containing information about candidates' test results. data = pd.read_csv('candidates_test_scores.csv') # Display first few rows of dataframe to understand structure. print(data.head()) # Perform simple descriptive analysis. summary_statistics = data.describe() print(summary_statistics) # Identify potential correlations between different features within the dataset. correlation_matrix = data.corr() print(correlation_matrix) ```
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值