Home /

Research

Showing 181 - 186 / 897

Auto Learning Attention


Authors:  BentengMa, JingZhang, YongXia....
Published date-12/01/2020
Tasks:  ImageClassification, KeypointDetection, ObjectDetection

Abstract: Attention modules have been demonstrated effective in strengthening the representation ability of a neural network via reweighting spatial or channel features or stacking both operations sequentially. However, designing the structures …

Revisiting Parameter Sharing for Automatic Neural Channel Number Search


Authors:  JiaxingWang, HaoliBai, JiaxiangWu....
Published date-12/01/2020
Tasks:  NeuralArchitectureSearch

Abstract: Recent advances in neural architecture search inspire many channel number search algorithms~(CNS) for convolutional neural networks. To improve searching efficiency, parameter sharing is widely applied, which reuses parameters among different …

Weak Form Generalized Hamiltonian Learning


Authors:  KevinCourse, TreforEvans, PrasanthNair....
Published date-12/01/2020
Tasks:  TimeSeries

Abstract: We present a method for learning generalized Hamiltonian decompositions of ordinary differential equations given a set of noisy time series measurements. Our method simultaneously learns a continuous time model and …

Optimal Adaptive Electrode Selection to Maximize Simultaneously Recorded Neuron Yield


Authors:  JohnChoi, KrishanKumar, MohammadKhazali....
Published date-12/01/2020

Abstract: Neural-Matrix style, high-density electrode arrays for brain-machine interfaces (BMIs) and neuroscientific research require the use of multiplexing: Each recording channel can be routed to one of several electrode sites on …

Learning with Operator-valued Kernels in Reproducing Kernel Krein Spaces


Authors:  AkashSaha, BalamuruganPalaniappan....
Published date-12/01/2020

Abstract: Operator-valued kernels have shown promise in supervised learning problems with functional inputs and functional outputs. The crucial (and possibly restrictive) assumption of positive definiteness of operator-valued kernels has been instrumental …

Look-ahead Meta Learning for Continual Learning


Authors:  GunshiGupta, KarmeshYadav, LiamPaull....
Published date-12/01/2020
Tasks:  ContinualLearning, Meta-Learning

Abstract: The continual learning problem involves training models with limited capacity to perform well on a set of an unknown number of sequentially arriving tasks. While meta-learning shows great potential for …

Filter by

Categories

Tags