Skip to content

Assignments and Projects from the MVA Master at ENS Paris-Saclay

Notifications You must be signed in to change notification settings

MatiasEtcheve/MVA

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Assignments Master Mathématiques Vision Apprentissage (MVA) at ENS Paris-Saclay

List of projects and assignements done during the master MVA. Some courses which did not required assignments are not here.

First semester

Application de l'analyse de données, des statistiques descriptives et de l'apprentissage automatique dans l'industrie aéronautique (AERO) by J. Lacaille:

  • Article review on A Multi-ELM Model for Incomplete Data
  • Repository which simply consists in getting our hands on flight data

Advanced learning for text and graph data (ALTEGRAD) by M. Vazirgiannis:

  • Lab 1: Hierarchical Attention Network
  • Lab 2: Transfert Learning
  • Lab 3: NLP Frameworks
  • Lab 4: Graph Mining
  • Lab 5: Deep Walk & Graph Convolutional Network
  • Lab 6: Deep Learning
  • Lab 7: Proteins
  • Project: Cellular Component Ontology Prediction

Image denoising : the human machine competition (IMDEN) by JM. Morel, G. Facciolo and P. Arias:

  • Lab 1: Multi-scale DCT
  • Lab 2: Non Local Means
  • Lab 3: Patch Similarity
  • Lab 4: EPLL
  • Lab 5: CNN Denoising
  • Lab 6: Deep CNN Denoising
  • Lab 7: Noise2Noise
  • Lab 8: U-Net

Reconnaissance d’objets et vision artificielle (RECVIS) by J. Sivic, J. Ponce, I. Laptev and C. Schmid:

  • Lab 1: Instance-level Recognition
  • Lab 2: Neural Networks
  • Lab 3: Image Classification
  • Project: Transporter Networks

Reinforcement Learning (RL) by M. Pirotta:

  • Lab 1: Dynamic Programming
  • Lab 2: Reinforce Learning
  • Lab 3: Bandits

Second semester

Audio Signal Analysis, Indexing and Transformation (ASA) by R. Badeau and G. Richard:

  • Lab 1: Multipitch
  • Lab 2: Effets / Reverb
  • Lab 3: HRTF
  • Lab 4: Modification
  • Lab 5: Separation
  • Project: not done

Graphs in Machine Learning (GML) by D. Calandriello and M. Valko:

  • Lab 1: Spectral Clustering
  • Lab 2: Semi-Supervised Learning
  • Lab 3: Graph Neural Networks

Machine learning with kernel methods (KM) by M. Arbel, A. Rudi, J-P. Vert and J. Mairal:

  • Lab 1: RKHS
  • Lab 2: SVC
  • Lab 3: Bn-splines and Sobolev spaces
  • Project: Graph Classification

Machine Learning for Time Series (TS) by L. Oudre and C. Truong. Work done in collaboration with Amric Trudel:

  • Lab 1: Dictionary learning
  • Lab 2: AR and MA processes
  • Lab 3: Change point detection and graph signals
  • Project: Multivariate Temporal Dictionary Learning for EEG

Algorithms for speech and natural language processing (SLP) by E. Dupoux, B. Sagot:

  • Project: Character tokenizer