Which of the following can correctly describe supervised learning vs unsupervised learning:()
A. With tags vs without tags
B. Classification vs clustering
Classification at the same time vs. clustering first and then qualitative
D. Independent vs non-independent
查看答案
The reason why deep neural networks in deep learning generally do not use BP algorithm is:()
A. During feedback adjustment, the gradient becomes more and more sparse, and the error correction signal becomes smaller and smaller from the top layer
B. Convergence is easy to the local minimum, because it is initialized with random values, it is easy to cause this situation when the initial value is far from the optimal area
C. The BP algorithm requires labeled data to train, but most of the data is unlabeled
D. Multi-layer network, only the nodes between adjacent layers are connected and cannot be corrected
Dimensionality reduction method:()
A. The original features are transformed into fewer new features through mapping and transformation.
By approximately linearizing Da's original features into fewer new features.
C. Select some of the most representative features from the original features.
D. Select some features that appear more frequently from the original features.
Criteria for "understanding" of natural language: input a natural language text to the computer, if the computer can ()
A. Questions and answers
B. Digest generation
C. Interpretation
D. Translation
In the self-emergence of the biological grid structure, the following are the main grid cell generation models()
A. Oscillation interference model
B. Continuous attractor network (CAN)
C. Hidden Markov model
Discriminant model
微信支付 
支付宝支付