Course on Continual Learning (given at ESSAI 2023)

5 lectures on continual learning, given at ESSAI 2023.

Dynastic Potential Crossover Operator

An optimal recombination operator for two-parent solutions provides the best solution among those that take the value for each variable from one of the parents (gene transmission property). If the solutions are bit strings, the offspring of an optimal recombination operator is optimal in the smallest hyperplane containing the two parent solutions. Exploring this hyperplane is computationally costly, in general, requiring exponential time in the worst case. However, when the variable interaction graph of the objective function is sparse, exploration can be done in polynomial time. In this article, we present a recombination operator, called Dynastic Potential Crossover (DPX), that runs in polynomial time and behaves like an optimal recombination operator for low-epistasis combinatorial problems. We compare this operator, both theoretically and experimentally, with traditional crossover operators, like uniform crossover and network crossover, and with two recently defined efficient recombination operators: partition crossover and articulation points partition crossover. The empirical comparison uses NKQ Landscapes and MAX-SAT instances. DPX outperforms the other crossover operators in terms of quality of the offspring and provides better results included in a trajectory and a population-based metaheuristic, but it requires more time and memory to compute the offspring.

Real-World Data Science Projects Management

Real-World Data Science Projects involve the practical application of data science methodologies to solve real-world problems. These projects require interdisciplinary collaboration, deal with large and complex datasets, and encompass the entire project lifecycle from data collection to deployment. Ethical considerations and advanced analytics techniques are also key aspects of these projects.

Gray Box Optimization

In Gray Box Optimization, the optimizer is given access to the set of M subfunctions. We prove Gray Box Optimization can efficiently compute hyperplane averages to solve non-deceptive problems in time. Bounded separable problems are also solved in time. As a result, Gray Box Optimization is able to solve many commonly used problems from the evolutional computation literature in evaluations.

AI Studies Survey

AI is a rapidly emerging field that has opened up new vistas of innovation and creativity. From intelligent systems to self-driving cars, AI has transformed the way we live and work. While AI is often studied as a subfield of computer science, it has grown so rapidly that it now encompasses many other fields. The World Economic Forum predicts a 37% increase in AI-related jobs by 2025. Therefore, it’s possible to imagine AI as a standalone field of study, independent of computer science.

Should you require access to the resource, please contact the author directly.

Machine Listening for Music and Sound Analysis

This lecture is held every winter semester as part of the Audio Signal Processing & Audio Systems Module at TU Ilmenau. In the first two lectures, we provide foundational knowledge about audio signal processing, audio representations, machine learning, and deep learning. Then, in four application lectures, concrete use-cases and research questions from music information retrieval and environmental sound analysis will be introduced.