Skip to main content
Cross Validated

Return to Question

edited title; changed tag; edited for English; light formatting; removed extra comments
Source Link
gung - Reinstate Monica
gung - Reinstate Monica
  • 147.5k
  • 89
  • 406
  • 717

Identify the linear How to identify linearly separable datasets

I am new in ML (almost one year doing some work in this field). I have a question regarding to identify the linear separable datasets and the approach I always do.

Usually, when I am given a dataset of dim<=3$d\le 3$, I just plot the data and observe if linearlinearly separable behaviour exists. When the dataset is of high dimensiondimensionality, I always follow a simple trick to identify if such dataset of high dimensionit is linearly separable or not: I run an SVM classifier using Linear kernel, and if the resulting accuracy is high (more than 90%), then I can say this dataset is linearly separable. If not, then I know this dataset is not linearlinearly separable soso I go to sophisticated ML algorithms like Neural Networkneural networks. Do you think this is a good approach?

Identify the linear separable datasets

I am new in ML (almost one year doing some work in this field). I have a question regarding to identify the linear separable datasets and the approach I always do.

Usually, when I am given a dataset of dim<=3, I just plot the data and observe if linear separable behaviour exists. When the dataset is of high dimension, I always follow a simple trick to identify if such dataset of high dimension is linearly separable or not: I run SVM classifier using Linear kernel, if the resulting accuracy is high (more than 90%), then I can say this dataset is linearly separable. If not, then I know this dataset is not linear separable so I go to sophisticated ML algorithms like Neural Network. Do you think this is a good approach?

How to identify linearly separable datasets

Usually, when I am given a dataset of $d\le 3$, I just plot the data and observe if linearly separable behaviour exists. When the dataset is of high dimensionality, I always follow a simple trick to identify if it is linearly separable or not: I run an SVM classifier using Linear kernel, and if the resulting accuracy is high (more than 90%), then I can say this dataset is linearly separable. If not, then I know this dataset is not linearly separable so I go to sophisticated ML algorithms like neural networks. Do you think this is a good approach?

deleted 12 characters in body
Source Link
kjetil b halvorsen ♦
kjetil b halvorsen ♦
  • 82.8k
  • 32
  • 201
  • 663

I am new in ML (almost one year doing some work in this field). I have a question regarding to identify the linear separable datasets and the approach I always do.

Usually, when I am given a dataset of dim<=3, I just plot the data and observe if linear separable behaviour exists. When the dataset is of high dimension, I always follow a simple trick to identify if such dataset of high dimension is linearly separable or not: I run SVM classifier using Linear kernel, if the resulting accuracy is high (more than 90%), then I can say this dataset is linearly separable. If not, then I know this dataset is not linear separable so I go to sophisticated ML algorithms like Neural Network. Do you think this is a good approach?

Thank you

I am new in ML (almost one year doing some work in this field). I have a question regarding to identify the linear separable datasets and the approach I always do.

Usually, when I am given a dataset of dim<=3, I just plot the data and observe if linear separable behaviour exists. When the dataset is of high dimension, I always follow a simple trick to identify if such dataset of high dimension is linearly separable or not: I run SVM classifier using Linear kernel, if the resulting accuracy is high (more than 90%), then I can say this dataset is linearly separable. If not, then I know this dataset is not linear separable so I go to sophisticated ML algorithms like Neural Network. Do you think this is a good approach?

Thank you

I am new in ML (almost one year doing some work in this field). I have a question regarding to identify the linear separable datasets and the approach I always do.

Usually, when I am given a dataset of dim<=3, I just plot the data and observe if linear separable behaviour exists. When the dataset is of high dimension, I always follow a simple trick to identify if such dataset of high dimension is linearly separable or not: I run SVM classifier using Linear kernel, if the resulting accuracy is high (more than 90%), then I can say this dataset is linearly separable. If not, then I know this dataset is not linear separable so I go to sophisticated ML algorithms like Neural Network. Do you think this is a good approach?

Source Link
steve
steve
  • 133
  • 2
  • 7

Identify the linear separable datasets

I am new in ML (almost one year doing some work in this field). I have a question regarding to identify the linear separable datasets and the approach I always do.

Usually, when I am given a dataset of dim<=3, I just plot the data and observe if linear separable behaviour exists. When the dataset is of high dimension, I always follow a simple trick to identify if such dataset of high dimension is linearly separable or not: I run SVM classifier using Linear kernel, if the resulting accuracy is high (more than 90%), then I can say this dataset is linearly separable. If not, then I know this dataset is not linear separable so I go to sophisticated ML algorithms like Neural Network. Do you think this is a good approach?

Thank you