This course covers advanced topics in deep learning architectures for natural language processing. The focus is on attention-based architectures, structure processing and variational-Bayesian approaches, and why these models are particularly suited to the ...
Ce cours est une introduction à la linguistique, discipline qui étudie les unités et les règles des langues humaines et rend compte de leur fonctionnement et de leurs fonctions. ...
The Human Language Technology (HLT) course introduces methods and applications for language processing and generation, using statistical learning and neural networks. ...
Probabilistic proof systems (eg PCPs and IPs) have had a tremendous impact on theoretical computer science, as well as on real-world secure systems. They underlie delegation of computation protocols and hardness of approximation. This course covers the fou ...
The students understand tools from the statistical physics of disordered systems, and apply them to study computational and statistical problems in graph theory, discrete optimisation, inference and machine learning. ...
In this course we study mathematical models of neurons and neuronal networks in the context of biology and establish links to models of cognition. The focus is on brain dynamics approximated by deterministic or stochastic differential equations. ...
This lecture presents ongoing work on how scientific questions can be tackled using machine learning. Machine learning enables extracting knowledge from data computationally and in an automatized way. We will learn on examples how this is influencing the v ...
This course integrates knowledge in basic, systems, clinical and computational neuroscience, and engineering with the goal of translating this integrated knowledge into the development of novel methods, technology for the clinical application for patients ...
The Loss Landscape of Neural Networks is in general non-convex and rough, but recent mathematical results lead provide insights of practical relevance.
9 online lectures, lecturers from NYU, Stanford, Shanghai, IST Austria, Google, Facebook, EPFL. ...
Probabilistic proof system (eg PCPs and IPs) have had a tremendous impact on the theoretical computer science, and have also found practical uses. They underlie delegation of computation protocols and hardness of approximation. This course covers the found ...