Softskills Seminar

Content

This course is an obligatory course of the M2 of the Master’s program “Data AI” of the Institut Polytechnique de Paris - open to students of other programs as well. The purpose of this course is to train students to give scientific presentations.

Every student chooses one research paper from the list of proposed papers. The student then prepares a 30min presentation about this paper. For this purpose, she/he can request the help of the advisor of the paper (by email and/or by meeting with them). The student then gives the presentation in the allocated time slot of the Softskills seminar, in the presence of the lecturer. Students are warmly encouraged to take into account the advice on giving good talks dispensed during the first session.

Each presentation is followed by a question-answer session, where both the students and the lecturers can ask the presenter questions about the paper. To animate this, each student is assigned to some other paper as the “devil’s advocate”. In this role (which is not known to the other students), she or he prepares some questions for the presenter. However, all students are invited to participate in the question-answer session.

Grading

The course is graded by

Schedule

The course takes place on Monday afternoon, 13:30-16:30 in Amphi 3 at Telecom Paris. The talks are at 13:30, 14:30, and 15:30.

Due to a spike in Corona infections, it is also possible to follow the course online here.

2021-11-22: Introduction
  1. Introduction
  2. How to give good talks
  3. How to do a PhD
2021-11-29: Talks
  1. Tiphaine Viard 1: Mathematics and the Internet: A Source of Enormous Confusion and Great Potential (Olivier LAURENT)
  2. Florence d'Alché 1: Oops I Took A Gradient: Scalable Sampling for Discrete Distributions (Alexandre Bodinier)
  3. Florence d'Alché 2: Eigengame (Aloysio Galvão Lopes)
  4. Fabian Suchanek 2: AnyBurl: Reinforced Anytime Bottom Up Rule Learning for Knowledge Graph Completion (Gurami Keretchashvili)
  5. Tiphaine Viard 2: Emergence of Scaling in Random Networks
2021-12-06: Talks
  1. Jean-Louis Dessalles 2: Right for the wrong reasons: Diagnosing syntactic heuristics in natural language inference (Temur MALISHAVA)
  2. Sophie Chabridon 1: Machine learning based concept drift detection for predictive maintenance (Akshaya Krishnamoorthy)
  3. Ada Diaconescu 1: A Macro-Level Order Metric for Self-Organizing Adaptive Systems (Victoire Hélouis)
  4. Jean-Louis Dessalles 1: Emergent Symbols through Binding in External Memory
2021-12-13: Talks
  1. Fabian Suchanek 1: Robust Discovery of Positive and Negative Rules in Knowledge Bases (Anthony Aoun)
  2. Goran Frehse 2: Observational Overfitting in Reinforcement Learning (Charlotte Juston)
  3. Goran Frehse 1: A predictive safety filter for learning-based control of constrained nonlinear dynamical systems (Moïne Satouri)
  4. Oana Bălălău 1: Self-training Improves Pre-training for Natural Language Understanding (Ali KESHAVARZI)
2022-01-03: Talks
This session is moved to 2022-01-24.
2022-01-10: Talks
  1. Louis Jachiet 1: Bao: Making Learned Query Optimization Practical (Nghia NGUYEN DANH)
  2. Mounîm A. El-Yacoubi 1 (Louis Jachiet): A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAI (Yi ZHANG)
  3. Mounîm A. El-Yacoubi 2 (Louis Jachiet): AI2: Safety and Robustness Certification of Neural Networks with Abstract Interpretation (Saad Lahlali)
2022-01-17: Talks
  1. Julien Alexandre dit Sandretto 1: Revising Hull and Box Consistency (Duo WANG)
  2. Pietro Gori 1: A Simple Framework for Contrastive Learning of Visual Representations (Imad Eddine MAROUF)
  3. Pierre-Henri Paris 1: Revisiting Semantics for Epistemic Extensions of Description Logics (Guanlin LI)
  4. Ioana Manolescu 2: Cloudburst: Stateful Functions-as-a-Service
2022-01-24: Talks (NEW)
  1. Julien Romero 1: PRIDE: Predicting Relationships in Conversations (Ariel NORA)
  2. Julien Romero 2: Pre-trained Language Model based Ranking in Baidu Search (Ng Man Chun)
  3. Chloé Clavel 1: Pretraining Methods for Dialog Context Representation Learning (Guillaume Barrhe)
  4. Mounîm A. El-Yacoubi 3: Threat of Adversarial Attacks on Deep Learning in Computer Vision: Survey (Soheila Masoudian)
2022-01-31: Talks (NEW)
  1. Ioana Manolescu 1: Towards scalable dataframe systems (Sini SURESH)