In this paper we propose a technique which avoids the evaluation of certain convolutional filters in a deep neural network. This allows to trade-off the accuracy of a deep neural network with the computational and memory requirements. This is especially important on a constrained device unable to hold all the weights of the network in memory.

This study uses a revolutionary image recognition method, deep learning, for the classification of potentially malignant pulmonary nodules. Deep learning is based on deep neural networks. We report results of our initial findings and compare performance of deep neural nets using a combination of different network topologies and optimization parameters. Classification accuracy, sensitivity and s...

Deep convolutional neural networks (CNNs) have demonstrated impressive performance on visual object classification tasks. In addition, it is a useful model for predication of neuronal responses recorded in visual system. However, there is still no clear understanding of what CNNs learn in terms of visual neuronal circuits. Visualizing CNN’s features to obtain possible connections to neuronscien...

This paper presents our investigations of recurrent neural networks (RNNs) for the phrase break prediction task. With the advent of deep learning, there have been attempts to apply deep neural networks (DNNs) to phrase break prediction. While deep neural networks are able to effectively capture dependencies across features, they lack the ability to capture long-term relations that are spread ov...

ii

Sarcasm detection has been modeled as a binary document classification task, with rich features being defined manually over input documents. Traditional models employ discrete manual features to address the task, with much research effect being devoted to the design of effective feature templates. We investigate the use of neural network for tweet sarcasm detection, and compare the effects of t...

In this paper, we propose a new image instance segmentation method that segments individual glands (instances) in colon histology images. This is a task called instance segmentation that has recently become increasingly important. The problem is challenging since not only do the glands need to be segmented from the complex background, they are also required to be individually identified. Here w...

Deep neural networks have shown recent promise in many language-related tasks such as the modelling of conversations. We extend RNN-based sequence to sequence models to capture the long-range discourse across many turns of conversation. We perform a sensitivity analysis on how much additional context affects performance, and provide quantitative and qualitative evidence that these models can ca...