人们在思考时并不总是从零开始,过去思考的结果将为未来的思考提供一定的支

People do not always start from scratch when thinking. The results of past thinking will provide certain support for future thinking. For example, in a conversation, the meaning of a sentence is understood from the context, rather than starting from the beginning. Traditional neural networks cannot achieve this function. For example, although a convolutional neural network can classify images, it may not be able to analyze the association of each image in the video. The information of the previous image cannot be used for the analysis of the latter image, and the recurrent neural network can solve this problem. Recursive neural network is used to process sequence data. Sequence data refers to data collected at multiple points in time, representing the state or degree of changes in things or phenomena over time. But sequence data has a characteristic, that is, the latter is related to the previous data [42]. Traditional neural networks can only establish weight connections between layers, while recurrent neural networks can also establish weight connections between neurons.

People don't always start from scratch when they think, and the results of past thinking will provide some support for future thinking. For example, in a conversation, a sentence means to be understood in context, not from scratch. Traditional neural networks cannot do this. For example, while convolutional neural networks can classify images, they may not be able to analyze the associations of each image in a video. The information of the previous image cannot be used for the analysis of the latter image, and recursive neural networks can solve this problem. The sequence data is processed by recursive neural network. Sequence data is data collected at multiple points in time, indicating the state or extent to which a thing or phenomenon changes over time. However, the sequence data has a characteristic, that is, the latter is related to the previous data. Traditional neural networks can only establish weight connections between layers, while recursive neural networks can also establish weight connections between neurons.

People don't always start from scratch when thinking. The results of past thinking will provide some support for future thinking. For example, in a conversation, the meaning of a sentence is understood according to the context, not from the beginning. Traditional neural network can not achieve this function. For example, although convolutional neural network can classify images, it may not be able to analyze the association of each image in the video. The information of the former image can not be used for the analysis of the latter image, and recurrent neural network can solve this problem. The recurrent neural network is used to process the sequence data. Sequence data refers to the data collected at multiple time points, indicating the state or degree of things or phenomena changing with time. However, sequence data has one feature, that is, the latter is related to the previous data [42]. The traditional neural network can only establish the weight connection between layers, while the recurrent neural network can also establish the weight connection between neurons.<br>