What are the difference between traditional machine learning and deep learning?

olive.zhao · Created Jan 28, 2021 10:52:13

Hello, friend!

Have a nice day!

As a model based on unsupervised feature learning and feature hierarchy learning, deep learning has great advantages in fields such as computer vision, speech recognition, and natural language processing.

Traditional Machine Learningc	Deep Learning
Low hardware requirements on the computer: Given the limited computing amount, the computer does not need a GPU for parallel computing generally.	Higher hardware requirements on the computer: To execute matrix operations on massive data, the computer needs a GPU to perform parallel computing.
Applicable to training under a small data amount and whose performance cannot be improved continuously as the data amount increases.	The performance can be high when high-dimensional weight parameters and massive training data are provided.
Level-by-level problem breakdown	E2E learning
Manual feature selection	Algorithm-based automatic feature extraction
Easy-to-explain features	Hard-to-explain features

Hope this helps!

liqiang185 · Created Jan 28, 2021 10:50:30

Hello, friend.
It's nice to meet you in the community.
We're working on your problem. Please be patient.

olive.zhao · Created Jan 28, 2021 10:52:13

Hello, friend!

Have a nice day!

As a model based on unsupervised feature learning and feature hierarchy learning, deep learning has great advantages in fields such as computer vision, speech recognition, and natural language processing.

Traditional Machine Learningc	Deep Learning
Low hardware requirements on the computer: Given the limited computing amount, the computer does not need a GPU for parallel computing generally.	Higher hardware requirements on the computer: To execute matrix operations on massive data, the computer needs a GPU to perform parallel computing.
Applicable to training under a small data amount and whose performance cannot be improved continuously as the data amount increases.	The performance can be high when high-dimensional weight parameters and massive training data are provided.
Level-by-level problem breakdown	E2E learning
Manual feature selection	Algorithm-based automatic feature extraction
Easy-to-explain features	Hard-to-explain features

Hope this helps!

What are the difference between traditional machine learning and deep learning?

Recommended answer

Third Party’s Trade Secret

`@trans`drinking_poetry`~trans`

My Followers

Enterprise

Consumer

Corporate

Carriers

What are the difference between traditional machine learning and deep learning?

Recommended answer

Third Party’s Trade Secret

`@trans`drinking_poetry`~trans`

My Followers