Skip to yearly menu bar Skip to main content


Poster

Deep Neural Nets with Interpolating Function as Output Activation

Bao Wang · Xiyang Luo · Zhen Li · Wei Zhu · Zuoqiang Shi · Stanley Osher

Room 517 AB #124

Keywords: [ Deep Learning ] [ CNN Architectures ]


Abstract:

We replace the output layer of deep neural nets, typically the softmax function, by a novel interpolating function. And we propose end-to-end training and testing algorithms for this new architecture. Compared to classical neural nets with softmax function as output activation, the surrogate with interpolating function as output activation combines advantages of both deep and manifold learning. The new framework demonstrates the following major advantages: First, it is better applicable to the case with insufficient training data. Second, it significantly improves the generalization accuracy on a wide variety of networks. The algorithm is implemented in PyTorch, and the code is available at https://github.com/ BaoWangMath/DNN-DataDependentActivation.

Live content is unavailable. Log in and register to view live content