Binary Deep Learning: Binary Weights and Semantic Binary Data Compression

Improving the efficiency in deploying deep neural networks (DNNs) and processing complex high-dimensional data has drawn increasing attention in recent years. Yet, the deployment of large DNN models is challenged by the high computational complexity and energy consumption, making it difficult to run on resource-constrained devices such as mobile...

The Estimation of Acoustic Parameters and Representations based on Room Impulse Responses

We are surrounded by all kinds of sounds at all times. What we hear varies with the physical environment and our position. Room impulse responses (RIRs) characterize the effect of the environment on a sound produced by a source. A first goal of this dissertation is to analyze RIRs and investigate how to extract environmental information from...

Efficiency in Deep Learning: Image and Video Deep Model Efficiency

Deep learning is the core algorithmic tool for automatically processing large amounts of data. Deep learning models are defined as a stack of functions (called layers) with millions of parameters, that are updated during training by fitting them to data. Deep learning models have show remarkable accuracy gains on visual problems in video and...

AI-Assisted Design & Optimization for Predictive Maintenance: A Case Study using Deep Learning and Search Metaheuristics for Structural Health Monitoring in Aviation

One of the classical solutions to maintain the aircraft structural integrity is to rely on the analysis of non-destructive testing (NDT) inspector with various inspection methods. However, it is relatively expensive in matter of time and costs to train human resources until the certification is reached. Further, in majority of the cases of...

Surface-related multiple estimation and removal with focus on shallow water

For exploration and development of the earth, seismic surveys are acquired to provide information about the subsurface, within specifications of accuracy set by geologists and engineers, and within business constraints on budgets and turn-around time for processing and interpretation of the data. The case of seismic surveys that are acquired,...

Data-efficient learning of geometric structures from single-view images

The humanly constructed world is well-organized in space. A prominent feature of this artificial world is the presence of repetitive structures and coherent patterns, such as lines, junctions, wireframes of a building, and footprints of a city. These structures and patterns facilitate visual scene understanding by providing abundant geometry...

Sample effficient deep reinforcement learning for control

The arrival of intelligent, general-purpose robots that can learn to perform new tasks autonomously has been promised for a long time now. Deep reinforcement learning, which combines reinforcement learning with deep neural network function approximation, has the potential to enable robots to learn to perform a wide range of new tasks while...