Combinatorial Convolutional Neural Networks for Words
This work tackles the problem of identifying combinatorial patterns in data for applications like word classification, but it appears incremental as it builds on existing neural network methods without claiming broad SOTA results.
The paper addresses the limitation of deep learning models in recognizing combinatorial patterns invariant under bijective transformations, proposing a combinatorial convolutional neural network for word classification to demonstrate feasibility.
The paper discusses the limitations of deep learning models in identifying and utilizing features that remain invariant under a bijective transformation on the data entries, which we refer to as combinatorial patterns. We argue that the identification of such patterns may be important for certain applications and suggest providing neural networks with information that fully describes the combinatorial patterns of input entries and allows the network to determine what is relevant for prediction. To demonstrate the feasibility of this approach, we present a combinatorial convolutional neural network for word classification.