Instituto de Telecomunicações and the Portuguese IEEE-AP, ED, MTT Joint Chapter, are pleased to invite you to the talk Towards Extreme Bandwidth Communications, by the Distinguished Professor Mohamed-Slim Alouini from the King Abdullah University of Science and Technology. The talk will take place in person and online, on June 29, 2022, at 15:30 pm in Room LT2, Torre Norte, 4th floor, Instituto Superior Técnico.
A rapid increase in the use of wireless services over the last few decades has led to the problem of radiofrequency (RF) spectrum exhaustion. More specifically, due to this RF spectrum scarcity, additional RF bandwidth allocation, as utilized in the recent past over "traditional bands", is not anymore enough to fulfill the demand for more wireless applications and higher data rates. The talk goes first over the potential offered by extreme band communication (XB-Com) systems to relieve spectrum scarcity. It then summarizes some of the challenges that need to be surpassed before such kinds of systems can be deployed. Finally, the talk offers an overview of some recent studies illustrating how different XB-Com technologies can collaborate to increase emerging and future networks' reliability and coverage while maintaining their high capacity.
Mohamed-Slim Alouini was born in Tunis, Tunisia. He received his Ph.D. degree in Electrical Engineering from the California Institute of Technology (Caltech) in 1998. He served as a faculty member at the University of Minnesota then in the Texas A&M University at Qatar before joining in 2009 the King Abdullah University of Science and Technology (KAUST) where he is now a Distinguished Professor of Electrical and Computer Engineering. Alouini is a Fellow of the IEEE and of Optica (formerly OSA). He is currently particularly interested in addressing the technical challenges associated with the uneven distribution, access to, and use of information and communication technologies in far-flung, rural, low-density populations, low-income, and/or hard-to-reach areas.
To participate online, follow the Zoom link:
https://videoconf-colibri.zoom.us/j/84195004891?pwd=iUnVB-Mh8Znlifo0U9s3SvRIOMYbjb.1 (Password: 262929)
Admission is free, but registration is required for logistics organization. Please follow the link below:
Project DeepSPIN presents on June 20, 2022, from 10:30 am to 12:00 am, the Workshops "Improving Systematic Generalization of Sequence-to-Sequence Learning with Structural Biases" and "Decoding is deciding under uncertainty - the case of NMT", respectively, with the invited keynote speakers Ivan Titov (University of Edinburgh) e Wilker Aziz (University of Amsterdam).
10:30 | Ivan Titov (University of Edinburgh)
Title: Improving Systematic Generalization of Sequence-to-Sequence Learning with Structural Biases
Abstract: Despite success in many domains, sequence-to-sequence models struggle in settings where train and test examples are drawn from different distributions. In particular, in contrast to humans, they fail to generalize systematically, i.e., interpret sentences representing novel combinations of concepts (e.g., text segments) seen in training. In this talk, I will discuss two main routes to improving systematic generalization. First, I will discuss the integration of structural biases into the model architecture. I will introduce a neural model which models the 'translation' process as structured permutation and monotonic translation of the subsequences. Second, I will discuss the injection of structural biases into the learning objectives. We use a meta-learning-like objective that encourages the gradients of similarly-structured examples (as determined by a similarity metric, e.g., a string or tree kernel) to be similar. This objective aims to inhibit memorization and encourages the model to learn the tasks in a 'systematic fashion'. We will use semantic parsing and machine translation as applications for our methods.
Joint work with Bailin Wang, Hal Conklin, Mirella Lapata, and Kenny Smith.
Bio: Ivan Titov is a professor and chair for NLP at the University of Edinburgh, and a part-time faculty member at the University of Amsterdam. Now, he is visiting researcher at Google. He received his Ph.D. from the University of Geneva and also spent time at the University of Illinois in Urbana-Champaign and the Saarland University. His current research focuses on natural language understanding, improving generalization across tasks and data distributions, and interpretability. He has been awarded an ERC starting grant, Dutch VICI, and VIDI fellowships. Ivan co-directs the Edinburgh doctoral school in NLP (CDT in NLP) and directs the Edinburgh ELLIS unit. He has been a program chair for ICLR 2021 and CoNLL 2018, an action editor at TACL and JMLR, and a member of the advisory board of the European chapter of ACL. He is a Turing and ELLIS fellow and co-directs ELLIS NLP program.
11:15 | Wilker Aziz (University of Amsterdam)
Title: Decoding is deciding under uncertainty — the case of NMT.
Abstract: In neural machine translation (NMT), we search for the mode of the model distribution to form predictions. We do so mostly following the intuition that the most probable outcome ought to be an essential distribution summary. Despite our intuition, there’s plenty of evidence against the adequacy of the most probable translations in NMT. In this talk, I make a case to move away from mode-seeking search as a tool for decision-making and model criticism. I will highlight reasons concerning MT as a task, NMT as a probabilistic model, and MLE as a training algorithm. Finally, I’ll turn to statistical decision theory and motivate a different rule for making decisions, one which is familiar to statistical MT folks like those of my generation and earlier, as well as a modern approximation of it. I’ll close the talk with a discussion of the merits and limitations of this decision rule, and comments on opportunities moving forward with or without a mode-seeking search.