Search Results for author:
Found 5 papers, 1 papers with code
Hierarchical Quantized Autoencoders
Despite progress in training neural networks for lossy image compression, current approaches fail to maintain both perceptual quality and abstract features at very low bitrates.
Texture Bias Of CNNs Limits Few-Shot Classification Performance
Accurate image classification given small amounts of labelled data (few-shot classification) remains an open problem in computer vision.
Discriminative training of RNNLMs with the average word error criterion
By fine-tuning the RNNLM on lattices with the average edit distance loss, we show that we obtain a 1. 9% relative improvement in word error rate over a purely generatively trained model.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
The Speechmatics Parallel Corpus Filtering System for WMT18
Our entry to the parallel corpus filtering task uses a two-step strategy.
Scaling Recurrent Neural Network Language Models
This paper investigates the scaling properties of Recurrent Neural Network Language Models (RNNLMs).
