Page 3 - Hikvision - Deep Learning
P. 3
ANTAGES OF 2. From “Shallow” to “Deep”
DEEP LEARNING
The algorithmic model for deep learning has a much deeper structure than the two 3-layered structures of
1. Traditional Intelligent Algorithm traditional algorithms. In deep learning, an original signal passes through layers of processing; next, it takes a
partial understanding (shallow) to an overall abstraction (deep) where it can perceive an object.
The number of video surveillance devices and the sheer
amount of data are both rapidly increasing in their own
rite, while the traditional intelligent algorithm continues
to operate only on the surface level. Current systems
suffer from：
Low Poor 3. From “Artificial Features” to “Feature Learning”
Accuracy Environmental
Suitability Deep learning does not require manual intervention but relies on a computer to extract features by itself. The more
Fewer features there are, the more accurate the recognition and classifications will be.
Recognition
Types
02
DEEP LEARNING
The algorithmic model for deep learning has a much deeper structure than the two 3-layered structures of
1. Traditional Intelligent Algorithm traditional algorithms. In deep learning, an original signal passes through layers of processing; next, it takes a
partial understanding (shallow) to an overall abstraction (deep) where it can perceive an object.
The number of video surveillance devices and the sheer
amount of data are both rapidly increasing in their own
rite, while the traditional intelligent algorithm continues
to operate only on the surface level. Current systems
suffer from：
Low Poor 3. From “Artificial Features” to “Feature Learning”
Accuracy Environmental
Suitability Deep learning does not require manual intervention but relies on a computer to extract features by itself. The more
Fewer features there are, the more accurate the recognition and classifications will be.
Recognition
Types
02
