CKConv: Continuous Kernel Convolution For Sequential Data

Understand

Conventional neural architectures for sequential data present important limitations.

• Recurrent networks suffer from exploding and vanishing gradients, small effective memory horizons, and must be trained sequentially.
• Convolutional networks are unable to handle sequences of unknown size and their memory horizon must be defined a priori.
• In this work, we show that all these problems can be solved by formulating convolutional kernels in CNNs as continuous functions.