In this paper we present a novel transliteration technique which is based on deep belief networks. Common approaches use finite state machines or other methods similar to conventional machine translation. Instead of using conventional NLP techniques, the approach presented here builds on deep belief networks, a technique which was shown to work well for other machine learning problems. We show ...

Deep features, defined as the activations of hidden layers of a neural network, have given promising results applied to various vision tasks. In this paper, we explore the usefulness and transferability of deep features, applied in the context of the problem of keyword spotting (KWS). We use a state-ofthe-art deep convolutional network to extract deep features. The optimal parameters concerning...

This paper introduces a novel architecture for reinforcement learning with deep neural networks designed to handle state and action spaces characterized by natural language, as found in text-based games. Termed a deep reinforcement relevance network (DRRN), the architecture represents action and state spaces with separate embedding vectors, which are combined with an interaction function to app...

We present several equilibrium runs under varying atmospheric CO2 concentrations using the University of Victoria Earth System Climate Model (UVic ESCM). The model shows two very different responses: for CO2 concentrations of 400 ppm or lower, the system evolves into an equilibrium state. For CO2 concentrations of 440 ppm or higher, the system starts oscillating between a state with vigorous de...