Andrew Ng gives a nice rule of thumb explanation in this video starting 14:46, though the whole video is worth watching.

Key Points

• Use linear kernel when number of features is larger than number of observations.
• Use gaussian kernel when number of observations is larger than number of features.
• If number of observations is larger than 50,000 speed could be an issue when using gaussian kernel; hence, one might want to use linear kernel.

Andrew Ng gives a nice rule of thumb explanation in this video starting 14:46, though the whole video is worth watching.

Key Points

• Use linear kernel when number of features is larger than number of observations.
• Use gaussian kernel when number of observations is larger than number of features.
• If number of observations is larger than 50,000 speed could be an issue when using gaussian kernel; hence, one might want to use linear kernel.

Andrew Ng gives a nice rule of thumb explanation in this video starting 14:46, though the whole videos is worth watching.

Key Points

• Use linear kernel when number of features is larger when number of observations.
• Use gaussian kernel when number of observations is larger than number of features.
• If number of observations is larger than 50,000 speed could be an issue when using gaussian kernel; hence, one might want to use linear.

Andrew Ng gives a nice rule of thumb explanation in this video starting 14:46, though the whole video is worth watching.

Key Points

• Use linear kernel when number of features is larger than number of observations.
• Use gaussian kernel when number of observations is larger than number of features.
• If number of observations is larger than 50,000 speed could be an issue when using gaussian kernel; hence, one might want to use linear kernel.