OpenAI describes Whisper as an encoder-decoder transformer, a type of neural network that can use context gleaned from input data to learn associations that can then be translated into the model's ...

2023.220148 discusses the direct field-to-pattern monolithic design of holographic metasurface via residual encoder-decoder convolutional neural network. Metasurfaces, as two-dimensional ...

In this way, image and video coding can be achieved using end-to-end neural network architectures ... Since both encoder and decoder models are learned (meaning they can be re-trained), the ...