先学计算机视觉还是机器学习
I’ve recently participated in a visual challenge as a part of my task for phase 1 in Machine Learning Scholarship Program for Microsoft Azure 2020 Organised by Udacity and Microsoft. I’ve prepared some visuals/Diagrams to explain some terms/topics used in Machine Learning. I’m sharing them in this blog.
我最近参加了一次视觉挑战,这是我由Udacity和Microsoft组织的Microsoft Azure 2020机器学习奖学金计划第一阶段任务的一部分。 我准备了一些视觉效果/图表来解释机器学习中使用的一些术语/主题。 我在此博客中分享。
I’ve tried to draw diagrams and other visuals to explain following topics
我试图绘制图表和其他视觉效果来解释以下主题
Difference between Machine Learning Algorithm and Machine Learning Model
机器学习算法与机器学习模型之间的区别
Difference between supervised and unsupervised learning
有监督学习与无监督学习之间的区别
Clustering
聚类
Underfitting, Overfitting , Bestfitting
拟合不足,拟合过度,最佳拟合
Difference between Parametric and non-parametric algorithm
参数和非参数算法之间的区别
Different types of Classifiers.
不同类型的分类器。
机器学习算法与机器学习模型 (Machine Learning Algorithm VS Machine Learning Model)
When Machine Learning Algorithm is trained with data it becomes Machine Learning model.
使用数据训练机器学习算法后,它将成为机器学习模型。
As you can see I have used equation of linear regression algorithm. it has coefficients B0 and B1. when it is trained with input and output, from training data it figures out the values for B0 and B1, for this case i assumed the value is 5, 6 . thus it becomes a model and now capable of predicting output (y) for unseen input (x).
如您所见,我使用了线性回归算法的方程式。 它具有系数B0和B1。 当使用输入和输出对其进行训练时,从训练数据中得出B0和B1的值,在这种情况下,我假设该值为5、6。 因此,它成为一个模型,现在能够预测看不见的输入(x)的输出(y)。
有监督的VS无监督的学习 (Supervised VS Unsupervised learning)
![Image for post](https://i-blog.csdnimg.cn/blog_migrate/c9476570a257f43810ceadce84644737.png)
In this visual i tried to simplify highlight the key difference between supervised and unsupervised approach of machine learning .
在这个视觉效果中,我试图简化突出显示机器学习的监督方法与无监督方法之间的关键区别。
In supervised approach data are labelled, in the first diagram you can see the model is trained with labelled data of Class A, Class B and Class C, and for new data the trained model predicts the Class.
在有监督的方法中标记数据,在第一个图中,您可以看到使用A,B和C类标记数据训练了模型,对于新数据,训练后的模型预测了该模型。
In Unsupervised approach there data are not labelled. for second diagram you can see the model is trained with pictures of apple and grape. the model figures out the hidden pattern of the data and make a cluster of data having similar pattern.
在无监督方法中,未标记数据。 对于第二张图,您可以看到模型是用苹果和葡萄的图片训练的。 该模型找出数据的隐藏模式,并形成具有相似模式的数据集群。
聚类 (CLUSTERING)
![Image for post](https://i-blog.csdnimg.cn/blog_migrate/96ef232a6f3af3466bfdeb5798f17e61.png)
In short clustering is just grouping the data having similar pattern together.
简而言之,聚类只是将具有相似模式的数据分组在一起。
Clustering is an unsupervised machine learning approach, where models are trained with unlabelled data. when the clustering models are trained they figure out the hidden pattern of data and group the similar data together.
聚类是一种无监督的机器学习方法,其中使用未标记的数据训练模型。 当训练聚类模型时,他们找出隐藏的数据模式并将相似的数据分组在一起。
欠拟合VS过度拟合VS最佳拟合 (Underfitting VS Overfitting VS Bestfitting)
![Image for post](https://i-blog.csdnimg.cn/blog_migrate/b2865f2ba625cca13d17778a5de62738.png)
Underfitting models tend to have high bias, Model with high bias make more assumption about target function, for the first character “ noodles “ can be represented as an incorrect assumption that model is making as a result it performs bad in both training and testing
拟合不足的模型倾向于具有较高的偏差,具有较高偏差的模型会对目标功能有更多的假设,因为第一个字符“ 面条 ”可以表示为一个错误的假设,即模型在训练和测试中均表现不佳
In Overfitting, the models pick up all the noises from the dataset, and fails to generalize for new dataset. for the second character by “ Memoizing word by word ” he may perform good for seen data even get 100/100 but when new questions are given he may fail to generalize.
在“过度拟合”中,模型会拾取数据集中的所有噪声,而无法归纳为新数据集。 对于第二个字符,通过“逐字记忆” ,即使看到的数据达到100/100,他的表现也可能很好,但是当给出新的问题时,他可能无法概括。
For Besfitting model, the models learn and perform well both in training and testing. best fitting models have balanced bias and variance error.
对于Besfiting模型,模型在训练和测试中都学习并表现良好。 最佳拟合模型具有平衡的偏差和方差误差。
参数VS非参数机器学习算法 (Parametric VS Non-parametric Machine Learning Algorithm)
![Image for post](https://i-blog.csdnimg.cn/blog_migrate/d8588bc6387f89a4e4f189cb0878cd18.png)
In parametric Machine Learning algorithm, the mapping function is assumed and and it has fixed number of inputs. for my diagram i represented the function with Y=B0 + B1X1 + B2X2.
在参数机器学习算法中,假定了映射函数,并且映射函数具有固定的输入数量。 对于我的图表,我用Y = B0 + B1X1 + B2X2表示该函数。
Example: Linear regression Algorithm
示例:线性回归算法
![Image for post](https://i-blog.csdnimg.cn/blog_migrate/7b5910f35e48814173933ff6326b7317.png)
Non-parametric Machine Learning algorithms are flexible, mapping function is not fixed, the inputs are flexible.
非参数机器学习算法灵活,映射功能不固定,输入灵活。
Example: Deep learning algorithms
示例:深度学习算法
不同类型的分类器 (Different types of Classifiers)
![Image for post](https://i-blog.csdnimg.cn/blog_migrate/07a989bc67e2791715c161253e95318e.png)
So there are mainly 3 types of classifiers.
因此,主要有3种类型的分类器。
For Binary classifiers there are only 2 classes and the output belongs to one class only.
对于二元分类器,只有2个类别,输出仅属于一个类别。
Example: suppose you are training a model to identify the image of dog and cat. there are 2 classes and the output will either be dog or car but not both.
示例:假设您正在训练一个模型来识别猫和狗的形象。 有2个类别,输出将是dog或car,但两者都不是。
For Multi-class single label classifiers the class number is more then 2, and output belongs to only one class.
对于多类别单标签分类器,类别号大于2,并且输出仅属于一个类别。
Example: suppose you are training a model to identify the image of dog, cat and rabbit. there are 3 classes and the output will belong to only one class
示例:假设您正在训练一个模型来识别狗,猫和兔子的图像。 有3个类别,输出将仅属于一个类别
For Multi-class multi label classifiers the class number is more then 2, and output can belong more the one class.
对于多类别多标签分类器,类别编号大于2,并且输出可以属于一个类别。
Example: suppose you are training a model do assign tags for articles based on the contents , one articles can have multiple tags
示例:假设您正在训练一个模型,请根据内容为文章分配标签,一个文章可以有多个标签
先学计算机视觉还是机器学习