Top best answers to the question «What is major disadvantage of neural network»
Disadvantages include its "black box" nature, greater computational burden, proneness to overfitting, and the empirical nature of model development. An overview of the features of neural networks and logistic regression is presented, and the advantages and disadvantages of using this modeling technique are discussed.
Arguably, the best-known disadvantage of neural networks is their “black box” nature. Simply put, you don't know how or why your NN came up with a certain output.
9 other answers
The benefits of neural networks involve high quality and accuracy in outputs. Your human workforce, no matter how many times they check for errors, can still leave some flaws unnoticed and that s what you want to eliminate as the CEO of your company. You need accuracy and quality in every big and small task.
There’s also another major disadvantage in using neural networks. This time, the issue has to do more with the bias of human programmers than strictly with information theory. Machine learning is excessive and unnecessary for many common tasks.
Here are some of the disadvantages of the neural network. Black box: One of the most distinguishing disadvantages of the neural network is their ‘’black box” nature. It means that we don’t know how and why the neural network came up with a certain output.
Disadvantages of Artificial Neural Networks (ANN) Hardware Dependence: Artificial Neural Networks require processors with parallel processing power, by their structure. For this reason, the realization of the equipment is dependent. Unexplained functioning of the
Disadvantages of Artificial Neural Networks (ANN) Hardware dependence: Artificial neural networks require processors with parallel processing power, by their structure. For this reason, the realization of the equipment is dependent. Unexplained functioning of the network: This is the most important problem of ANN.
The major disadvantage of RNNs are the vanishing gradient and gradient exploding problem. It makes the training of RNN difficult in several ways. It cannot process very long sequences if it uses tanh as its activation function
Gradual corruption: A network slows over time and undergoes relative degradation. The network problem does not immediately corrode immediately.
A convolution is a significantly slower operation than, say maxpool, both forward and backward. If the network is pretty deep, each training step is going to take much longer. The network is a bit too slow and complicated if you just want a good pre-trained model
Arguably, the best-known disadvantage of neural networks is their “black box” nature. Simply put, you don’t know how or why your NN came up with a certain output. For example, when you put an image of a cat into a neural network and it predicts it to be a car, it is very hard to understand what caused it to arrive at this prediction.