-
limitations. The field of interpretable machine learning aims to fill this gap by developing interpretable models and algorithms for learning from data. Meanwhile, the field of knowledge discovery and data
-
optimizations tailored to different environments. The optimizations range from algebraic optimizations (e.g., term rewriting) to algorithmic optimizations (e.g., group level algorithms), and to hardware
-
interpretable models and algorithms for learning from data. Meanwhile, the field of knowledge discovery and data mining has allowed us to obtain insights from large amounts of data for decades, and it is worth
-
., term rewriting) to algorithmic optimizations (e.g., group level algorithms), and to hardware optimizations (e.g., automated pipelining). The PhD student will be supervised by Nusa Zidaric. Key
-
of topics include algorithmic fairness in network analysis, developing network embedding frameworks for real-world network datasets or AI models based on agentic LLMs for simulating real-world network data