February Data Science meet-up

Data science meetups are back!

We are happy to invite you to our second meet-up in 2023 with two speakers: Dr. Nilotpal Sinha and Hazem FAHMY. You will meet with new people, network with people who share common interests and enjoy lite snacks!

Dr. Nilotpal Sinha is a post-doctoral researcher in SnT in University of Luxembourg and his research interest is Artificial Intelligence, AutoML, Evolutionary Computation, Signal Processing, Neural Architecture Search, Computer Vision, Edge AI. The title of his presentation is "Neural Architecture Search using Evolutionary Algorithms":

```
Abstract:
Neural Architecture Search (NAS) deals with designing algorithms that automatically design artificial neural networks. It has been used to design convolutional neural networks (CNN) for computer vision task that outperform the human-designed architectures. In this talk, I will introduce my works on neural architecture search and how evolutionary algorithms are used to design the architecture of neural networks for a given task.
```

Hazem FAHMY is a Doctoral researcher in SnT in University of Luxembourg and the title of his presentation is "Simulator-based explanation and debugging of hazard-triggering events in DNN-based safety-critical systems":

```
Abstract:
When Deep Neural Networks (DNNs) are used in safety-critical systems, engineers should determine the safety risks associated with failures (i.e., erroneous outputs) observed during testing. For DNNs processing images, engineers visually inspect all failure-inducing images to determine common characteristics among them. Such characteristics correspond to hazard-triggering events (e.g., low illumination) that are essential inputs for safety analysis. Though informative, such activity is expensive and error-prone.To support such safety analysis practices, we propose SEDE, a technique that generates readable descriptions for commonalities in failure-inducing, real-world images and improves the DNN through effective retraining. SEDE leverages the availability of simulators, which are commonly used for cyber-physical systems. It relies on genetic algorithms to drive simulators towards the generation of images that are similar to failure-inducing, real-world images in the test set; it then employs rule learning algorithms to derive expressions that capture commonalities in terms of simulator parameter values. The derived expressions are then used to generate additional images to retrain and improve the DNN.With DNNs performing in-car sensing tasks, SEDE successfully characterized hazard-triggering events leading to a DNN accuracy drop. Also, SEDE enabled retraining leading to significant improvements in DNN accuracy, up to 18 percentage points.
```