Talks

  • Neural Potts Model. MLCB 2020 - Machine Learning in Computational Biology.

  • Generative Adversarial Networks – hands-on tutorial in pytorch. NYC AI & ML meetup. [Slides]

    Github Repository with notebook This talk is a hands-on live coding tutorial. We will implement a Generative Adversarial Network (GAN) to learn to generate small images. We will assume only a superficial familiarity with deep learning and a notion of PyTorch. This tutorial is as self-contained as possible. The goal is that this talk/tutorial can serve as an introduction to PyTorch at the same time as being an introduction to GANs.

  • Guest Lecture: Deep Learning. Intro to Data Science, Fall 2018 @ CCNY. [Slides]

    Guest Lecture: intro to Deep Learning. The class was a 1 hour lecture and 1 hour lab for undergrad students in Computer Science at CCNY (college of CUNY).

  • Machine Learning: successes, promises and limits. AI Academy Seminars (Howest and Voka) at Kortrijk, Belgium. [Slides]

    Seminar at AI Academy, organized by Howest and Voka, Flanders, Belgium. This seminar presented my view of AI / machine learning / deep learning for a non-technical audience of business leaders in Kortrijk, Belgium. It’s high-level and accessible to a wide audience.

  • McGan: Mean and Covariance Feature Matching GAN. ICML 2017, Sydney, Australia. [Slides]

    Presentation of our paper https://arxiv.org/abs/1702.08398

  • Contributed Spotlight Talk. NIPS 2016 End-to-end Learning for Speech and Audio Processing Workshop. [Slides]

    Dense Prediction on Sequences with Time-Dilated Convolutions for Speech Recognition. http://arxiv.org/abs/1611.09288

  • Invited talks August and September 2016. Cambridge University Engineering Department, Cambridge, UK / KU Leuven, Belgium / RWTH Aachen, Germany / Ghent University, Belgium.

  • Talk at the NYU CILVR lab. New York City. [Slides]

    ConvNets for Speech - NYU Lab presentation

  • Very Deep Multilingual Convolutional Neural Networks for LVCSR. ICASSP 2016, Shanghai. [Slides]

subscribe via RSS