A neural Turing machine model with a novel memory module and a setting method thereof

Abstract

The invention discloses a neural Turing machine model with a novel memory module and a setting method thereof, belonging to the neural network field. The invention adds the double helix DNA structurein the memory module of the nerve Turing machine model. At the same time, the read-write head of neural Turing machine model is improved to adapt to the storage data of a double helix DNA structure ina memory module. A neural network controller dynamically reads and writes the timing data stored in the double helix DNA structure, with the current descendant data of the double helix DNA structureas input to the next neuron layer, the activation value of the next neuron is obtained by combining the contents currently read from the memory matrix, and is rewritten into the double helix DNA structure to replace the current descendant data, and the current descendant data before the replacement is converted into the parent data of the current descendant data after the replacement. At the sametime, the invention also discloses a corresponding training setting method. The invention updates the memory matrix of the memory module more meticulously and improves the stability of the model.

Description

technical field [0001] The invention belongs to the field of neural networks, and in particular relates to a neural Turing machine model with a novel memory module. Background technique [0002] Neural Turing Machines (Neural Turing Machines, NTM) as a new machine learning model, its essence is based on the recurrent neural network to add an additional addressable external memory, so as to improve the performance of the neural network and solve the problems of the recurrent neural network. some flaws. Traditional machine learning algorithms or neural networks have some limitations in the face of the few sample data in behavior detection, the wide variety of sensor combinations, and the difficulty in associating high-level data with underlying logic. On the other hand, the development of artificial intelligence will face a huge bottleneck in the future. The following three points must be the first to accept the challenge: insufficient sample size, insufficient generalization...

Images