patternMinor
What method of collective recogintion to use for digits recognition?
Viewed 0 times
recogintionrecognitioncollectivewhatmethoddigitsforuse
Problem
The structure of the question is as follows: at first, I provide the concept of collective recognition, further I provide explanation of the various methods of group classification that I found, in the end I introduce you the question. Those who are experts in this field and may not need explanations might just look at the headlines go straight to the question.
What is a collective recognition/classification
What is meant by the term collective recognition is the task of using multiple classifiers (committee, ensemble, etc.), each of which will decide on the class of one entity with the subsequent coordination of their decisions with the help of a certain algorithm. Using a set of classifiers, typically lead to higher recognition accuracy and better computational efficiency indicators.
Some approaches of multiple classifiers decisions integration:
Competence areas method
The idea of collective classification based on the competence areas is that each base classifier can work well in some feature space area (area of competence), excelling in this area remaining classifiers in terms of accuracy and reliability of decisions. The area of competence of each base classifier must somehow be estimated. Appropriate program called referee. Classification task is solved so that each algorithm is only used in its own competence area, i.e. where it produces the best results compared to other classifiers. At the same time in each area the decision of only one classifier is taken into account. However, you must have certain algorithm that for any input determines which of the classifiers is the most competent.
So, one approach suggests that with each classifier a special algorithm (the referee, which is designed to assess th
What is a collective recognition/classification
What is meant by the term collective recognition is the task of using multiple classifiers (committee, ensemble, etc.), each of which will decide on the class of one entity with the subsequent coordination of their decisions with the help of a certain algorithm. Using a set of classifiers, typically lead to higher recognition accuracy and better computational efficiency indicators.
Some approaches of multiple classifiers decisions integration:
- based on the concept of classifiers’ competence areas and procedures that assess the competence of classifiers with respect to each input of the classification system.
- methods for combining classifiers decisions based on the use of neural networks.
Competence areas method
The idea of collective classification based on the competence areas is that each base classifier can work well in some feature space area (area of competence), excelling in this area remaining classifiers in terms of accuracy and reliability of decisions. The area of competence of each base classifier must somehow be estimated. Appropriate program called referee. Classification task is solved so that each algorithm is only used in its own competence area, i.e. where it produces the best results compared to other classifiers. At the same time in each area the decision of only one classifier is taken into account. However, you must have certain algorithm that for any input determines which of the classifiers is the most competent.
So, one approach suggests that with each classifier a special algorithm (the referee, which is designed to assess th
Solution
The state of the art for digit recognition does not use collective recognition, competence areas, ensembles, or any of the other ideas you propose in your question.
Instead, the state of the art for digit recognition uses convolutional neural networks. Just a convolutional neural network: no need for multiple of them, no need for any kind of other fancy business on top of it. Instead, the state of the art focuses on the specific architecture of the convolutional neural network (e.g., how many layers? what types of pooling?) and on the training procedures (e.g., adjusting the learning rate in stochastic gradient descent, dropout, batch normalization, and more).
As far as I know, the same is true for the state of the art for object/symbol recognition.
So, my advice is: while all those concepts sound nice on paper, they don't seem to actually be needed or useful for the tasks you care about. You're better off ignoring those concepts. Sorry to be the bearer of bad news when you've obviously put a bunch of effort into typing up an explanation of those concepts.
Instead, the state of the art for digit recognition uses convolutional neural networks. Just a convolutional neural network: no need for multiple of them, no need for any kind of other fancy business on top of it. Instead, the state of the art focuses on the specific architecture of the convolutional neural network (e.g., how many layers? what types of pooling?) and on the training procedures (e.g., adjusting the learning rate in stochastic gradient descent, dropout, batch normalization, and more).
As far as I know, the same is true for the state of the art for object/symbol recognition.
So, my advice is: while all those concepts sound nice on paper, they don't seem to actually be needed or useful for the tasks you care about. You're better off ignoring those concepts. Sorry to be the bearer of bad news when you've obviously put a bunch of effort into typing up an explanation of those concepts.
Context
StackExchange Computer Science Q#62978, answer score: 4
Revisions (0)
No revisions yet.