BaSAL: Class Balanced Warm Start Active Learning for LiDAR Semantic Segmentation

Active learning has been proposed as a solution to mitigate the expensive and time-consuming process of annotating large-scale autonomous driving datasets. The process typically involves a model initialization phase, followed by multiple iterations aiming at selecting the most informative data based on the initial model. However, we find two...

Aligning AI with Human Norms: Multi-Objective Deep Reinforcement Learning with Active Preference Elicitation

The field of deep reinforcement learning has seen major successes recently, achieving superhuman performance in discrete games such as Go and the Atari domain, as well as astounding results in continuous robot locomotion tasks. However, the correct specification of human intentions in a reward function is highly challenging, which is why state...

Exploiting structure in counterexamples to speed up equivalence checking in the minimally adequate teacher framework: Active Learning

Active state machine learning algorithms are a class of algorithms that allow us to infer state machines representing certain systems. These algorithms interact with a system and build a hypothesis of what the state machine describing that system looks like according to the behavior they observed. Once the algorithm arrives at a hypothesis, it...

Population-based Active Learning for Black-Box Regression

Many applications employ models to represent real-life environments efficiently. To allow these models to be realistic it is commonly fitted using a dataset containing labeled samples. When obtaining a label for a sample from the environment is expensive, it is key that the dataset contains only those samples that aid in providing a realistic...

Sampling settings in active learning for investigating inconsistency

Active learning has the potential to reduce labeling costs in terms of time and money. In practical use, active learning works as an efficient data labeling strategy. Another point of view to look at active learning is to consider active learning as a learning problem, where the training data is queried by the active learner. Under this...

Discrete state-space active inference and unknown controlled state transitions

Active inference is a process theory arising from neuroscience which casts perception, action, planning and learning under one optimisation criterion: minimisation of free energy. Current literature on the implementation of discrete state-space active inference focuses on scalability, the comparison to reinforcement learning and its performance...

Active Semi-Supervised Learning For Diffusions on Graphs

In statistical learning over large data-sets, labeling all points is expensive and time-consuming. Semi-supervised classification allows learning with very few labels. Naturally, selecting a few points to label becomes crucial as the performance relies heavily on the labeled points. The motivation behind active learning is to build an optimal...

Investigation of active learning techniques for dynamic Time-of-Use (dToU) tariff policy design for residential users

The active learning approach is a special case of semi-supervised machine learning which is able to interactively query the user to reduce the uncertainty of the machine learning model. The approach is useful to minimize the data labeling cost. The project aims to study and use this method to characterize residential electricity users’ demand...

Active Learning for Overlay Prediction in Semi-conductor Manufacturing

In the manufacturing of semi-conductor devices there is a constant demand for increasing precision and yield. Measuring and controlling overlay errors is essential in this process, but these measurements are difficult and costly. Predictive models can be used as an addition to measurements, but they required labelled data for training. To...

Data Analytics in Web-based Education in the Higher-education Classroom

Attention span of students in a classroom is very short. To overcome this, different active learning methodologies have been used in the past. Active learning keeps the students busy and engaged throughout the lecture. It breaks the lecture into certain time intervals by intermixing breaks, demonstrations and questions after each interval. For...

Active Learning in Image Quality Assessment

A world without digital images is unthinkable in this era of information and communication technology. Billions of images are created, shared and ultimately enjoyed by users every day. However, digital images are sensitive to a wide variety of distortions during the delivery mechanism it goes through. Any of the distortions that can arise during...

Interactive 3D Segmentation of CT-scans of the Hip Joint, Using Active Learning to Select Delineation Planes

This paper evaluates a method that improves segmentation e ciency by intelligently suggesting planes where correction is most valuable. An existing method is extended to work for segmentation of multiple bones simultaneously. This method is evaluated because in clinical practice it is often necessary that scans are segmented very accurate. When...

Active Learning by Discrepancy Minimization: A Comparison of Active Learning Methods Motivated by Generalization Bounds

In many settings in practice it is expensive to obtain labeled data while unlabeled data is abundant. This is problematic if one wants to train accurate (supervised) predictive models. The main idea behind active learning is that models can perform better with less labeled data, if the model may choose the data from which it learns. Active...

Combining learning with fuzzing for software deobfuscation

Software obfuscation is widely applied to prevent reverse engineering of applications. However, to evaluate security and validate behaviour we are interested in analysis such software. In this thesis, we give an overview of available obfuscation techniques as well as methods to undo this effort through reverse engineering and deobfuscation. We...

Sample reusability in importance-weighted active learning

Recent advances in importance-weighted active learning solve many of the problems of traditional active learning strategies. But does importance-weighted active learning also produce a reusable sample selection? This thesis explains why reusability can be a problem, how importance-weighted active learning removes some of the barriers to...