머신러닝에서 쓰이는 인공신경망


 (ANN등..)이랑 PCA(주성분분석)이랑 결국은


모델 자체가 블랙박스화 되고 설명력을 직관적으로 알아낼 수 없다는 점에서는 일맥상통해?


검색해보니 아래와 같이 답이 있어서...


Both Principal Component Analysis(PCA) and Artificial Neural Networks (ANNs) can be considered black boxes in the sense that it can be difficult to understand how the model arrived at its outputs and to interpret the individual components or neurons that contribute to the final result.

In the case of PCA, the transformed data can be difficult to interpret, as the principal components are linear combinations of the original variables and may not have a clear meaning in the original context.

In the case of ANNs, the large number of neurons and connections in the network can make it challenging to understand how the individual neurons contribute to the final output. Additionally, the non-linear transformations performed by the neurons in the network can make it difficult to interpret the relationship between the inputs and outputs of the model.

There have been efforts to develop methods to increase the interpretability and transparency of both PCA and ANNs, but these methods are still an active area of research and may not be applicable in all cases. In some cases, it may be necessary to accept the black box nature of these models and rely on other methods, such as model performance on a validation set, to assess their quality and reliability.