Curriculum Learning for mmWave Beam Selection
Curriculum Learning Curriculum Learning [1] is a biologically inspired procedure to train machine learning models. While it is usual practice to train Neural Networks (NNs) using batches of data sampled uniformly in random from the training dataset, curriculum learning mimics the way humans learn, starting from simpler training samples that unveil general and raw concepts,…
Matteo Zecchin
More humanoid agents with Hierarchical Reinforcement Learning
As you may have guessed from its name, Hierarchical Reinforcement Learning (HRL) is a family of Reinforcement Learning algorithms that decompose the problem into different hierarchies of subproblems or subtasks, and the higher-qlevel tasks invoke the primitive lower-level tasks. The goal of HRL is to learn a multilayer policy to perform control at different levels…
Salman Mohebi
Industrial PhD
PhD or industry? One-million-dollar question: Going towards Academic field or Practical work? This is the most common question that will come to your mind after graduation. Each one of them has its advantages and disadvantages, so how should I pick one of them? I remember a piece of advice given to me by my professor during…
Sobhi Alfayoumi
How COVID-19 affected my research career
Picking a topic for this blog article really was a struggle. I had so many different ideas – a typical day in Ph.D. life, the experiences of working in a multicultural and international environment, moving to a foreign country, living abroad, cultural diversity, … . But then I thought: why not talk about the world’s…