Home /
Research
Showing 847 - 852 / 904
Intrinsic Robotic Introspection: Learning Internal States From Neuron Activations
NikosPitsillos, AmeyaPore, BjornSandJensen....
Published date-11/03/2020
We present an introspective framework inspired by the process of how humans perform introspection. Our working assumption is that neural network activations encode information, and building internal states from these …
Parameter Efficient Deep Neural Networks with Bilinear Projections
LitaoYu, YongshengGao, JunZhou....
Published date-11/03/2020
Recent research on deep neural networks (DNNs) has primarily focused on improving the model accuracy. Given a proper deep learning framework, it is generally possible to increase the depth or …
Towards a Universal Gating Network for Mixtures of Experts
ChenWenKang, ChuaMengHong, TomasMaul....
Published date-11/03/2020
The combination and aggregation of knowledge from multiple neural networks can be commonly seen in the form of mixtures of experts. However, such combinations are usually done using networks trained …
PyLightcurve-torch: a transit modelling package for deep learning applications in PyTorch
MarioMorvan, AngelosTsiaras, NikolaosNikolaou....
Published date-11/03/2020
We present a new open source python package, based on PyLightcurve and PyTorch, tailored for efficient computation and automatic differentiation of exoplanetary transits. The classes and functions implemented are fully …
Exploring DeshuffleGANs in Self-Supervised Generative Adversarial Networks
GulcinBaykal, FurkanOzcelik, GozdeUnal....
Published date-11/03/2020
ImageGeneration
Generative Adversarial Networks (GANs) have become the most used network models towards solving the problem of image generation. In recent years, self-supervised GANs are proposed to aid stabilized GAN training …
Learning 3D Dynamic Scene Representations for Robot Manipulation
ZhenjiaXu, ZhanpengHe, JiajunWu....
Published date-11/03/2020
3D scene representation for robot manipulation should capture three key object properties: permanency -- objects that become occluded over time continue to exist; amodal completeness -- objects have 3D occupancy, …