Related papers: David Brink: A long-standing teacher
The following paragraphs will describe the origins of John Rainwater, the impact of his work, the motivations for various parts of it and the prospects for his future.
Knowledge Distillation (KD) has proven effective for compressing large teacher models into smaller student models. While it is well known that student models can achieve similar accuracies as the teachers, it has also been shown that they…
As in school, one teacher to cover all subjects is insufficient to distill equally robust information to a student. Hence, each subject is taught by a highly specialised teacher. Following a similar philosophy, we propose a multiple…
Pretrained models have become a commodity and offer strong results on a broad range of tasks. In this work, we focus on classification and seek to learn a unique encoder able to take from several complementary pretrained models. We aim at…
Deep Learning is one of the newest trends in Machine Learning and Artificial Intelligence research. It is also one of the most popular scientific research trends now-a-days. Deep learning methods have brought revolutionary advances in…
Machine learning has seen a vast increase of interest in recent years, along with an abundance of learning resources. While conventional lectures provide students with important information and knowledge, we also believe that additional…
An obituary of J.R. Dorfman. The focus is on his scientific career and on his many important publications.
This is a reflection on the author's experience in teaching logic at the graduate level in a computer science department. The main lesson is that model building and the process of modelling must be placed at the centre stage of logic…
We give a brief account of some of the most spectacular results established by James Maynard for which he has been awarded the Fields Medal.
The present text summarizes several factors considered as essential for teacher education according to the state of current research and best practice, with a focus on science teacher education, and as realized at the University of Geneva.
Deep learning (DL) has gained much attention and become increasingly popular in modern data science. Computer scientists led the way in developing deep learning techniques, so the ideas and perspectives can seem alien to statisticians.…
Several thoughts are presented on the long ongoing difficulties both students and academics face related to Calculus 101. Some of these thoughts may have a more general interest.
I was lucky to meet (and even cooperate at some extent) with Israel M. Gelfand, and tried to write down (mainly in 2003-2013) my recollections about his work style and lessons I learned from him about teaching and writing mathematics…
Steven Weinberg productive scientific life teaches us many things, one of the most important of which is the power of his example. This essay contains personal reminiscences and a speculation about gravitational wave propagation based on…
In commemoration of the fifth anniversary since Nino Boccara's departure, this article offers some personal recollections and provides insight into his life and accomplishments. Detailed bibliography of his works is included together with…
Teaching is about constantly innovating strategies, ways and means to engage diverse students in active and meaningful learning. In line with this, SUTD adopts various student-centric teaching and learning teaching methods and approaches.…
During the five days of this workshop we had forty five hours of lectures, so a tremendous amount of new information was delivered. I will be able only to highlight some aspects of the numerous interesting topics, which were discussed,…
Lecture notes on selected topics in the theory of gravitation.
This is a brief account of the legacy of Ken Wilson in statistical physics, high energy physics, computing and education.
This paper summarizes some challenges encountered and best practices established in several years of teaching Machine Learning for the Physical Sciences at the undergraduate and graduate level. I discuss motivations for teaching ML to…