Question

In: Computer Science

list and discuss ten shortcomings of artificial neural networks

list and discuss ten shortcomings of artificial neural networks

Solutions

Expert Solution

Shortcomings of artificial neural networks:

1) Black box: The calculation of result is hidden. It is not known how data is processed.

2) Optimizing parameters: Optimizing the network can be challenging, as neural network requires  too many parameters.

3) Computationally expensive: Artificial neural networks are also more computationally expensive than traditional algorithms. It can take several weeks to train completely from scratch and requires high processing time for large neural networks.

4) Operation: The neural network needs training to operate.

5) Unpredictable behavior : Neural networks behaves a similar way the human brain does. They learn  by examples as they cannot be programmed to perform a specific task. Careful selection of examples is important as  network finds solution by itself and its operation can be unpredictable. This reduces trust in the network.

6) Determination of appropriate network structure: Determination of appropriate network structure is done through experience and trial and error as there is no specific rule defined for determining the structure.

7) The duration of the network is unknown: The network is reduced to a certain value(which is not optimal) of the error on the sample means that the training(period is unknown) has been completed.

8) Hardware dependence: According to the structure of artificial neural networks, they are dependent of equipment like, processors with parallel processing power.

9) Representing the problem to the network is difficult: As artificial neural networks works with numerical information, problems need to be translated into numerical value. Representation of the problem to artificial neural networks directly influences the performance of the network .

10) Large amount of data required for training: In general ,Neural networks usually require large amount of data for learning.


Related Solutions

Machine learning Neural Networks question: Which of the following statements is (are) true about neural networks?...
Machine learning Neural Networks question: Which of the following statements is (are) true about neural networks? There may be multiple correct statements, please give a reason why they are true or false (A) The training time depends on the size of the network as well as the training data. (B)The perceptron is a single layer recurrent neural network. (C) In image processing, compared with fully connected networks, usually convolutional networks are preferred. (D) Neural network cannot be used for solving...
What are neural networks, and how do neural networks relate to localized and global brain functioning?...
What are neural networks, and how do neural networks relate to localized and global brain functioning? What does our knowledge of neural networks tell us about how the brain processes information? How do PET scans and fMRI allow us to see the flow of information throughout networks?
What are neural networks, what is their purpose, and whatpractical applications for these networks in...
What are neural networks, what is their purpose, and what practical applications for these networks in medicine can you think of? Be brief in terms of the applications and examples, but you must be able to introduce and explain the concept of a neural network, clearly showing your understanding of the theory and briefly showing your practical vision.
Machine learning Neural Networks question: Which one statement is true about neural networks? (Select the single...
Machine learning Neural Networks question: Which one statement is true about neural networks? (Select the single best answer), and please explain why they are true or false: (A) We always train neural networks by optimising a convex cost function. (B) Neural networks are more robust to outliers than support vector machines. (C) Neural networks always output values between 0 and 1. (D) A neural network with a large number of parameters often can better use big training data than support...
Machine learning Neural Networks question: Which one statement is true about neural networks? (Select the single...
Machine learning Neural Networks question: Which one statement is true about neural networks? (Select the single best answer), and please explain why they are true or false: (A) We always train neural networks by optimising a convex cost function. (B) Neural networks are more robust to outliers than support vector machines. (C) Neural networks always output values between 0 and 1. (D) A neural network with a large number of parameters often can better use big training data than support...
List three arguments in favor of protectionist policies and discuss their shortcomings.
List three arguments in favor of protectionist policies and discuss their shortcomings.
Predictive Modeling Using Neural Networks (For SAS Enterprise Miner software) In preparation for a neural network...
Predictive Modeling Using Neural Networks (For SAS Enterprise Miner software) In preparation for a neural network model, is the imputation of missing values needed? Why or why not?
Briefly assess the relationships between Biological and Artificial Neural Network
Briefly assess the relationships between Biological and Artificial Neural Network
How would banks use neural networks with sas miner?
How would banks use neural networks with sas miner?
Which of the following statement is INCORRECT?   a. Neural networks mimic the way that human experts...
Which of the following statement is INCORRECT?   a. Neural networks mimic the way that human experts learn. b. Neural network is also called artificial neural networks. c. Neural networks cannot be used for prediction. d. Neural networks are based on a model of biological activity in the brain. What is the output of decision trees? a. A set of rules. b. A set of weights. c. A set of bias values. d. Distance measures. For a decision tree, the number...
ADVERTISEMENT
ADVERTISEMENT
ADVERTISEMENT