-
Accelerating Deep Learning by Focusing on the Biggest Losers
This paper introduces Selective-Backprop, a technique that accelerates t...
10/02/2019 ∙ by Angela H. Jiang, et al. ∙
669
∙
share
read it
-
Meta-learning algorithms for Few-Shot Computer Vision
Few-Shot Learning is the challenge of training a model with only a small...
09/30/2019 ∙ by Etienne Bennequin, et al. ∙
97
∙
share
read it
-
Mixout: Effective Regularization to Finetune Large-scale Pretrained Language Models
In natural language processing, it has been observed recently that gener...
09/25/2019 ∙ by Cheolhyoung Lee, et al. ∙
95
∙
share
read it
-
Kornia: an Open Source Differentiable Computer Vision Library for PyTorch
This work presents Kornia -- an open source computer vision library whic...
10/05/2019 ∙ by Edgar Riba, et al. ∙
93
∙
share
read it
-
GradVis: Visualization and Second Order Analysis of Optimization Surfaces during the Training of Deep Neural Networks
Current training methods for deep neural networks boil down to very high...
09/26/2019 ∙ by Avraam Chatzimichailidis, et al. ∙
90
∙
share
read it
-
Regression Planning Networks
Recent learning-to-plan methods have shown promising results on planning...
09/28/2019 ∙ by Danfei Xu, et al. ∙
87
∙
share
read it
-
DeepGCNs: Making GCNs Go as Deep as CNNs
Convolutional Neural Networks (CNNs) have been very successful at solvin...
10/15/2019 ∙ by Guohao Li, et al. ∙
86
∙
share
read it
-
A Topological Loss Function for Deep-Learning based Image Segmentation using Persistent Homology
We introduce a method for training neural networks to perform image or v...
10/04/2019 ∙ by James R. Clough, et al. ∙
85
∙
share
read it
-
Stacked Autoencoder Based Deep Random Vector Functional Link Neural Network for Classification
Extreme learning machine (ELM), which can be viewed as a variant of Rand...
10/04/2019 ∙ by Rakesh Katuwal, et al. ∙
77
∙
share
read it
-
Towards Explainable Artificial Intelligence
In recent years, machine learning (ML) has become a key enabling technol...
09/26/2019 ∙ by Wojciech Samek, et al. ∙
72
∙
share
read it
-
Synthetic Data for Deep Learning
Synthetic data is an increasingly popular tool for training deep learnin...
09/25/2019 ∙ by Sergey I. Nikolenko, et al. ∙
71
∙
share
read it
