Abstract: We develop an efficient computational solution to train deep neural networks (DNN) with free-form activation functions. To make the problem well-posed, we augment the cost functional of the ...
A Cycloidal Drive is a mechanism used in the engineering world as a speed reducer for an input shaft while reversing its direction. It can do this for high ratios in a small space. They do this using ...
STN is a powerful neural network architecture proposed by DeepMind in [1]. STN achieves real spatial invariance by automatically rectify input images before they are feeded into a normal ...
Abstract: Continuous-time trajectory representation has recently gained popularity for tasks where the fusion of high-frame-rate sensors and multiple unsynchronized devices is required. Lie group ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results