Increasing the Receptive Field of Neurons in Convolutional Neural Networks
S Shapovalova, Y Moskalenko… - Cybernetics and Systems …, 2023 - Springer
S Shapovalova, Y Moskalenko, O Baranichenko
Cybernetics and Systems Analysis, 2023•SpringerThe convolutional neural network architectures for classifying 1D and 2D signals are
analyzed. The authors have found that for a high-dimensional input signal, one can ensure
an adequate classification accuracy only by using a large number of layers. It is impossible
to achieve the required accuracy with limited computing resources. However, if the number
of layers is limited, the accuracy decreases, starting from some critical dimensionality value.
A method for modifying a convolutional neural network with relatively small number of layers …
analyzed. The authors have found that for a high-dimensional input signal, one can ensure
an adequate classification accuracy only by using a large number of layers. It is impossible
to achieve the required accuracy with limited computing resources. However, if the number
of layers is limited, the accuracy decreases, starting from some critical dimensionality value.
A method for modifying a convolutional neural network with relatively small number of layers …
The convolutional neural network architectures for classifying 1D and 2D signals are analyzed. The authors have found that for a high-dimensional input signal, one can ensure an adequate classification accuracy only by using a large number of layers. It is impossible to achieve the required accuracy with limited computing resources. However, if the number of layers is limited, the accuracy decreases, starting from some critical dimensionality value. A method for modifying a convolutional neural network with relatively small number of layers to solve this problem has been proposed. Its effectiveness has been experimentally proved.
Springer
以上显示的是最相近的搜索结果。 查看全部搜索结果