摘要
A new neuron model with a tunable activation function, denoted by the TAF model, and its application are addressed. The activation function as well as the connection weights of the neuron model can be adjusted in the training process The two-spiral problem was used as an example to show how to deduce the adjustable activation function required, and how to construct and train the network by the use of the a priori knowledge of the problem. Due to the incorporation of constraints known a priori into the activation function, many novel aspects are revealed, such as small network size, fast learning and good performances. It is believed that the introduction of the new neuron model will pave a new way in ANN studies.
A new neuron model with a tunable activation function, denoted by the TAF model, and its application are addressed. The activation function as well as the connection weights of the neuron model can be adjusted in the training process The two-spiral problem was used as an example to show how to deduce the adjustable activation function required, and how to construct and train the network by the use of the a priori knowledge of the problem. Due to the incorporation of constraints known a priori into the activation function, many novel aspects are revealed, such as small network size, fast learning and good performances. It is believed that the introduction of the new neuron model will pave a new way in ANN studies.
基金
Project supported hy the National Natural Science Foundation of China.
