Rethinking Online Action Detection in Untrimmed Videos: A Novel Online Evaluation Protocol

The Online Action Detection (OAD) problem needs to be revisited. Unlike traditional offline action detection approaches, where the evaluation metrics are clear and well established, in the OAD setting we find very few works and no consensus on the evaluation protocols to be used. In this work we propose to rethink the OAD scenario, clearly...

DeepSHM: A deep learning approach for structural health monitoring based on guided Lamb wave technique

In our previous work, we demonstrated how to use inductive bias to infuse a convolutional neural network (CNN) with domain knowledge from fatigue analysis for aircraft visual NDE. We extend this concept to SHM and therefore in this paper, we present a novel framework called DeepSHM which involves data augmentation of captured sensor signals...

Multidomain Graph Signal Processing: Learning and Sampling

In this era of data deluge, we are overwhelmed with massive volumes of extremely complex datasets. Data generated today is complex because it lacks a clear geometric structure, comes in great volumes, and it often contains information from multiple domains. In this thesis, we address these issues and propose two theoretical frameworks to handle...

Deep Reinforcement Learning for Goal-directed Visual Navigation

Safe navigation in a cluttered environment is a key capability for the autonomous operation of Micro Aerial Vehicles (MAVs). This work explores a (deep) Reinforcement Learning (RL) based approach for monocular vision based obstacle avoidance and goal directed navigation for MAVs in cluttered environments. We investigated this problem in the...

A Case for Deep Learning in Mining Software Repositories

Repository mining researchers have successfully applied machine learning in a variety of<br/>scenarios.  However, the use of deep learning in repository mining tasks is still in its infancy.<br/>In this thesis, we describe the advantages and disadvantages of using deep learning in mining software repository research and demonstrate these by...

Learning the scale of image features in Convolutional Neural Networks

The millions of filter weights in Convolutional Neural Networks (CNNs), all have a well-defined and analytical expression for the partial derivative to the loss function. Therefor these weights can be learned from data with a technique called gradient descent optimization. While the filter weights have a well-defined derivative, the filter size...

Multi-Sensor Human Detection on an Intelligent Security Robot

This thesis aims to combine visual data and distance measurements from a Laser Range Finder (LRF) to recognise the presence of humans. The data from the LRF is used to find regions of interest in order to reduce the load on the visual data analysis. Deep learning convolutional neural networks have shown incredible results on visual recognition...

Positive Class Localization Map: A framework for weakly supervised object localization

To possess a computer algorithm that can perform the popular task of object localization with only weak supervision is valuable for numerous reasons. Often enough a certain localization task (e.g. bird localization) simply does not have properly annotated training data available. In this thesis a novel approach called Positive Class Localization...

Tuning of Optical Beamforming Networks: A Deep Learning Approach

Optical beamforming networks (OBFNs), which consist of many small and flat antennas, called phased array antennas (PAAs), can be tuned such that the signal beam from the airplanes can be steered towards a satellite. This was proposed as a alternative to the mechanically steered antenna, which has many disadvantages. The problem of tuning a large...

Consolidated Deep Actor Critic Networks

The works [Volodymyr et al. Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602, 2013.] and [Volodymyr et al. Human-level control through deep reinforcement learning. Nature, 518(7540):529–533, 2015.] have demonstrated the power of combining deep neural networks with Watkins Q learning. They introduce deep Q networks ...

Consolidated Deep Actor Critic Networks (DRAFT)

The works [Volodymyr et al. Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602, 2013.] and [Volodymyr et al. Human-level control through deep reinforcement learning. Nature, 518(7540):529–533, 2015.] have demonstrated the power of combining deep neural networks with Watkins Q learning. They introduce deep Q networks ...