EfficientNet is a method that scales up convolutional neural networks with the help of compound coefficient and increases their performance.
Convolutional neural networks (CNNs) were first introduced in the 1980s. One of the first known examples of CNN was the Time Delay Neural Network (TDNN) developed in 1987 by
Alex Waibel and his research team. This CNN focused on speech recognition, including shift-invariant phoneme recognition.
Source:
https://antispoofing.org/EfficientNet_for_Deepfake_Detection:_Architecture,_Purpose_and_Practical_Application [antispoofing.org]