We propose a deep learning architecture to capture argumentative relations of attack and support from one piece of text to another, of the kind that naturally occur in a debate. The architecture uses two (unidirectional or bidirectional) Long ShortTerm Memory networks and (trained or non-trained) word embeddings, and allows to considerably improve upon existing techniques that use syntactic fea...

We study the automatic detection of suggestion expressing text among the opinionated text. The examples of such suggestions in online reviews would be, customer suggestions about improvement in a commercial entity, and advice to the fellow customers. We present a qualitative and quantitative analysis of suggestions present in the text samples obtained from social media platforms. Suggestion min...

In this paper we combine one method for hierarchical reinforcement learning—the options framework—with deep Q-networks (DQNs) through the use of different “option heads” on the policy network, and a supervisory network for choosing between the different options. We utilise our setup to investigate the effects of architectural constraints in subtasks with positive and negative transfer, across a...

Deep learning is a branch of machine learning and this technique allows us to create classifiers. We must find the best dataset size for a classifier process to permit using less time and give good accuracy. In this paper we will propose models with different deep layers and size dimensions for detecting the best model to solve a task that needs quick time processing.

Recently, deep learning techniques have enjoyed success in various multimedia applications, such as image classification and multi-modal data analysis. Large deep learning models are developed for learning rich representations of complex data. There are two challenges to overcome before deep learning can be widely adopted in multimedia and other applications. One is usability, namely the implem...

Deep learning applications are computationintensive and often employ GPU as the underlying computing devices. Deep learning frameworks provide powerful programming interfaces, but the gap between source codes and practical GPU operations make it difficult to analyze the performance of deep learning applications. In this paper, through examing the features of GPU traces and deep learning applica...

This paper presents a concept of a novel method for adjusting hyper-parameters in Deep Learning (DL) algorithms. An external agent-observer monitors a performance of a selected Deep Learning algorithm. The observer learns to model the DL algorithm using a series of random experiments. Consequently, it may be used for predicting a response of the DL algorithm in terms of a selected quality measu...

There are a huge number of ML methods, with new variants being invented every day. But the ways that one works with these various methods are very similar. Hence we are teaching this course to give students an introduction to the methodological and experimental issues involved in working with ML. To a large extent, the principles of good experimental practice are the same whether one is using a...

Random walks are at the heart of many existing deep learning algorithms for graph data. However, such algorithms have many limitations that arise from the use of random walks, e.g., the features resulting from these methods are unable to transfer to new nodes and graphs as they are tied to node identity. In this work, we introduce the notion of attributed random walks which serves as a basis fo...