Feasibility study on the integration of a deep learning dose computation algorithm in an automated proton therapy treatment planning system

The dose computation algorithm, or dose engine, is one of the fundamental parts of radiotherapy treatment planning. These algorithms predict how the dose will be distributed inside the patient.<br/>Current dose engines are mainly based on either Monte Carlo simulations (MC) or pencil beam algorithms (PBA). MC being very precise, but relatively...

Optimizing the pump schedule of water distribution systems using a deep learning meta-model: To what extent can algorithm unrolling optimize the pump schedule of an urban water distribution system?

This thesis investigates the integration of algorithm unrolling and genetic algorithms (GA) for optimizing pump scheduling in water distribution systems (WDS), a critical component for ensuring energy-efficient water delivery. In the context of modern civilization’s reliance on clean, affordable water for diverse uses, the operation of a WDS,...

Optimization of Strawberry Supply Chain from the Perspective of Producers

This thesis aims at maximizing the profit of a strawberry producer while satisfying the retailer's demand and meeting other constraints. The amount of strawberries to be delivered to the retailer signed in the contract is the main decision variable to be optimized in the problem. Furthermore, the transportation scheduling is also optimized to...

Deep Generative Design: A Deep Learning Framework for Optimized Spatial Truss Structures with Stock Constraints

Energy use, CO2 emissions, and waste production are all significant causes of environmental issues. The building sector is a major contributor to these problems, specifically the manufacturing of (structural) steel elements. Application of reuse and/or remanufacturing, as done in a circular economy, will reduce these effects. Therefore, these...

Understanding weight-magnitude hyperparameters in training binary networks

Binary Neural Networks (BNNs) are compact and efficient by using binary weights instead of real-valued weights. Current BNNs use latent real-valued weights during training, where several training hyper-parameters are inherited from real-valued networks. The interpretation of several of these hyperparameters is based on the magnitude of the real...

DMQL: Deep Maximum Q-Learning: Combatting Relative Overgeneralisation in Deep Independent Learners using Optimism and Similarity

Various pathologies can occur when independent learners are used in cooperative Multi-Agent Reinforcement Learning. One such pathology is Relative Overgeneralisation, which manifests when a suboptimal Nash Equilibrium in the joint action space of a problem is preferred over an optimal Equilibrium. Approaches exist to combat relative...

DeepONet Generated Optimal Test Functions for the Finite Element Method

The finite element method (FEM) is a numerical method that is used to approximate the solutions to partial differential equations when solutions in the classical sense do not exist or are very hard to find. The method is used to solve problems that are relevant for industries like the automotive industry, the petroleum industry, and the aviation...

Deep Neural Networks and Optimization: A promising tag team

Machine learning has been a computer sciences buzzword for years. The technology has a lot of potential and a huge number of applications that spoke to people with and without knowledge of computer sciences. Image, text and speech recognition, social profiling, computergames, everything seemed possible. Machine learning is not as much in the...

Generative CoLearn: steering and cost prediction with generative adversarial nets in kinodynamic RRT

Kinodynamic planning is motion planning in state space and aims to satisfy kinematic and dynamic constraints. To reduce its computational cost, a popular approach is to use sampling based methods such as RRT with off-line machine learning for estimating the steering cost and inputs. However, scalability and robustness are still open challenges...

Side-Channel Attacks using Convolutional Neural Networks: A Study on the performance of Convolutional Neural Networks on side-channel data

Side-Channel Attacks, are a prominent type of attacks, used to break cryptographic implementations on a computing system. They are based on information "leaked" by the hardware of a computing system, rather than the encryption algorithm itself. Recent studies showed that Side-Channel Attacks can be performed using Deep Learning models. In this...

Deep Reinforcement Learning - Pretraining actor-critic networks using state representation learning

In control, the objective is to find a mapping from states to actions that steer a system to a desired reference. A controller can be designed by an engineer, typically using some model of the system or it can be learned by an algorithm. Reinforcement Learning (RL) is one such algorithm. In RL, the controller is an agent that interacts with the...