Debasmita will present Aster, which automates mixed-precision fixed-point quantization for deep feed-forward neural networks. SPEAKER: Debasmita Lohar, Assist. Prof. at ITU. ABSTRACT: Neural networks are increasingly becoming integral to safety-critical applications,[…]
In this SQUARE talk, Ola will discuss how variational inference can be understood as projections that decide the visible shape of a posterior. SPEAKER: Ola Rønning, Postdoc at ITU. ABSTRACT: Exact[…]
Chinamyi Baramashetru is visiting SQUARE. In this SQUARE talk, Chinamyi will present her work on a type system for privacy-aware programming, focusing on enforcing GDPR-style consent and data-flow constraints through a[…]
In this SQUARE talk Raúl will discuss writing thread safe code using the Java Memory Model. SPEAKER: Raúl Pardo Jimenez, Assoc. prof. at ITU. ABSTRACT: In this talk, I will give[…]
In this talk, Peter will give some concrete examples of how to use ITU’s HPC cluster. SPEAKER: Peter Sestoft, prof. at ITU. ABSTRACT: : ITU’s HPC cluster offers access to a[…]
Olaya will give a practitioner’s introduction to GTSAM, a staple in vision-based SLAM. SPEAKER: Olaya Álvarez-Tuñón ABSTRACT: This talk provides an introduction to GTSAM (Georgia Tech Smoothing And Mapping), a library[…]
In this year’s first Square Talk, Debasmita discusses how sound mixed-precision tuning can achieve performance comparable to dynamic analysis while preserving correctness guarantees. This is joint work with Anastasia Isychev (TU[…]
In this year’s last SQUARE talk, Julie will examine the scale and broader impact of CERN’s contributions to open-source software. SPEAKER: Julie Skoven Hinge, M.Sc. student at ITU. TITLE: How to[…]
Olaya will discuss pose-graph estimation from visual odometry using metric-aware learning. SPEAKER: Olaya Alvarez Tunon, postdoc at ITU and AI & Robotics engineer at EIVA. TITLE: MAC-VO: Metrics-aware Covariance for Learning-based[…]
Ola will present an overview of certification for graph-based SLAM algorithms. SPEAKER: Ola Rønning, postdoc at ITU. TITLE: Certified SLAM — An Overview ABSTRACT: When cast as an optimization problem, SLAM[…]