Mike Chrzanowski

Learn More
We show that an end-to-end deep learning approach can be used to recognize either English or Mandarin Chinese speech–two vastly different languages. Because it replaces entire pipelines of hand-engineered components with neural networks , end-to-end learning allows us to handle a diverse variety of speech including noisy environments, accents and different(More)
This paper introduces a new technique for mapping Deep Recurrent Neural Networks (RNN) efficiently onto GPUs. We show how it is possible to achieve substantially higher computational throughput at low mini-batch sizes than direct implementations of RNNs based on matrix multiplications. The key to our approach is the use of persistent computational kernels(More)
Background: An increasing amount of research has emerged in the past few years using social media to either predict the outcomes of elections or, in the case of the United States, to classify users as Democrat or Republican. While predictions based on social media are not representative of the voting population, they have been shown to compete with surveys(More)
  • 1