Swiss Machine Learning Day
Event details
Date
07.11.2018
Hour
09:00
› 17:00
Speaker
09:15 – Crowd-Robot Interaction: Crowd-aware Robot Navigation with Attention-based Deep Reinforcement Learning (Changan Chen, EPFL) 09:30 – A Physically-Consistent Bayesian Non-Parametric Mixture Model for Dynamical System Learning (Nadia Figueroa, EPFL) 09:45 – Sample-Efficient Imitation Learning via Generative Adversarial Nets (Lionel Blonde, UNIGE) 10:00 – Sparsified SGD with Memory (Jean-Baptiste Cordonnier, EPFL) 10:15 – Local Rotation Invariance and Directional Sensitivity of 3D Texture Operators: Comparing Classical Radiomics, CNNs and Spherical Harmonics (Vincent Andrearczyk, HES/SO) 10:30 – Coffee break & Posters 11:15 – Not All Samples Are Created Equal: Deep Learning with Importance Sampling (Angelos Katharopoulos, IDIAP) 11:30 – Evading classifiers in discrete domains with provable optimality guarantees (Bogdan Kulynych, EPFL) 11:45 – Regression Concept Vectors and Bidirectional Explanations of Deep Learning predictions (Mara Graziani, HES/SO) 12:00 – Beyond Optimism: Information Directed Exploration in Bandits (Johannes Kirschner, ETHZ) 12:15 – CNN-based face presentation attack detection using patches of faces (Amir Mohammadi, IDIAP) 12:30 – Lunch 13:45 – Semi-blind spatially-variant deconvolution and focus estimation in optical microscopy by use of convolutional neural networks (Adrian Shajkofci, IDIAP) 14:00 – Efficient spherical Convolutional Neural Network with HEALPix sampling for cosmology (Nathanaël Perraudin, ETHZ) 14:15 – Weakly and unsupervised disentangling factors of variation (Attila Szabó, UNIBE) 14:30 – A few pixels can make a big difference (Apostolos Modas, EPFL) 14:45 – Deep Self-Organization: Interpretable Discrete Representation Learning on Time Series (Vincent Fortuin, ETHZ) 15:00 – Coffee break & Posters 15:45 – Autonomous Drone Racing (Elia Kaufmann, UZH) 16:00 – Privacy-Preserving Classification with Secret Vector Machines (Valentin Hartmann, EPFL) 16:15 – Patient-Attentive Sequential Strategy: A Reinforcement Learning-based Perimetry Test (Serife Kucur, UNIBE) 16:30 – Trace and Detect Adversarial Attacks on CNNs using Feature Response Maps. (Amirian Mohammadreza, ZHAW) 16:45 – Variational Methods to find all solutions of an Optimal Control problem (Thibaut Kulak, IDIAP)
Location
Swisstech Convention Center
Category
Conferences - Seminars
The Swiss Machine Learning Day is a one-day workshop organized every year since 2012, which aims at bringing together Swiss researchers working on topics related to machine learning
Practical information
Informed public
Registration required
