In this paper, we introduce a novel approach for systematically solving
...
Optimisers are an essential component for training machine learning mode...
Numerous recent works utilize bi-Lipschitz regularization of neural netw...
Multilingual models jointly pretrained on multiple languages have achiev...
Many gradient-based meta-learning methods assume a set of parameters tha...
Meta-learning of shared initialization parameters has shown to be highly...
Regularization and transfer learning are two popular techniques to enhan...
In realistic settings, a speaker recognition system needs to identify a
...
We propose a novel transductive inference framework for metric-based
met...
Recent metric-based meta-learning approaches, which learn a metric space...
While tasks could come with varying number of instances in realistic
set...
A machine learning model that generalizes well should obtain low errors ...
While variational dropout approaches have been shown to be effective for...
Attention mechanism is effective in both focusing the deep learning mode...
We propose DropMax, a stochastic version of softmax classifier which at ...
We propose Deep Asymmetric Multitask Feature Learning (Deep-AMTFL) which...