Συντάχθηκε 29-11-2018 13:23
Σεμινάριο MATLAB – Πολυτεχνείο Κρήτης
Τετάρτη 05.12.2018, ώρες: 13:00-16:00, Αμφιθέατρο Επιστημών
Ομιλητής: Γκέτσης Ζαχαρίας
Machine Learning and Deep Learning with MATLAB
|
Importing and Organizing Data
|
Objective: Bring data into MATLAB and organize it for analysis, including normalizing data and removing observations with missing values.
- Data types
- Tables
- Categorical data
- Data preparation
|
|
Finding Natural Patterns in Data (Clustering)
|
Objective: Use unsupervised learning techniques to group observations based on a set of explanatory variables and discover natural patterns in a data set.
- Unsupervised learning
- Clustering methods
- Cluster evaluation and interpretation
|
|
Building Classification Models
|
Objective: Use supervised learning techniques to perform predictive modeling for classification problems. Evaluate the accuracy of a predictive model.
- Supervised learning
- Training and validation
- Classification methods
|
|
Building Regression Models
|
Objective: Use supervised learning techniques to perform predictive modeling for continuous response variables.
- Parametric regression methods
- Nonparametric regression methods
- Evaluation of regression models
|
|
Creating Neural Networks
|
Objective: Create and train neural networks for clustering and predictive modeling. Adjust network architecture to improve performance.
- Clustering with Self-Organizing Maps
- Classification with feed-forward networks
- Regression with feed-forward networks
|
|
Transfer Learning for Image Classification
|
Objective: Perform image classification using pretrained networks. Use transfer learning to train customized classification networks.
- Pretrained networks
- Image datastores
- Transfer learning
- Network evaluation
|
|
Building Convolutional Networks
|
Objective: Build convolutional networks from scratch. Understand how information is passed between network layers and how different types of layers work. Train networks to locate and label specific objects within images.
- Training from scratch
- Neural networks, convolution layers and filters
- Object detection
|
Τόπος: Λ - Κτίριο Επιστημών/ΗΜΜΥ, 141Π-98,141Θ-97
Έναρξη: 05/12/2018 13:00
Λήξη: 05/12/2018 16:00
