DeepAI AI Chat
Log In Sign Up

Polynomial Networks in Deep Classifiers

by   Grigorios G. Chrysos, et al.

Deep neural networks have been the driving force behind the success in classification tasks, e.g., object and audio recognition. Impressive results and generalization have been achieved by a variety of recently proposed architectures, the majority of which are seemingly disconnected. In this work, we cast the study of deep classifiers under a unifying framework. In particular, we express state-of-the-art architectures (e.g., residual and non-local networks) in the form of different degree polynomials of the input. Our framework provides insights on the inductive biases of each model and enables natural extensions building upon their polynomial nature. The efficacy of the proposed models is evaluated on standard image and audio classification benchmarks. The expressivity of the proposed models is highlighted both in terms of increased model performance as well as model compression. Lastly, the extensions allowed by this taxonomy showcase benefits in the presence of limited data and long-tailed data distributions. We expect this taxonomy to provide links between existing domain-specific architectures.


Interpreting and Explaining Deep Neural Networks for Classification of Audio Signals

Interpretability of deep neural networks is a recently emerging area of ...

Randomly weighted CNNs for (music) audio classification

The computer vision literature shows that randomly weighted neural netwo...

Uncertainty Calibration for Deep Audio Classifiers

Although deep Neural Networks (DNNs) have achieved tremendous success in...

Wide and Deep Neural Networks Achieve Optimality for Classification

While neural networks are used for classification tasks across domains, ...

Adversarial Audio Synthesis with Complex-valued Polynomial Networks

Time-frequency (TF) representations in audio synthesis have been increas...