Adobe PDF (5.29 MB)
Title Details:
Machine Learning with Neural Nets
Authors: Symeonidis, Panagiotis
Description:
Abstract:
In chapter six we will study recommendation algorithms based on artificial neural networks. In particular, we will describe the Multi-layer Perceptron - (MLP), the basic, feedforward, multi-layered neural network. We will also detail Graph Convolutional Netwoks, Graph Neural Networks and Node Embeddings. Convolutional Neural Networks are particularly effective in image processing and recognition and, since an image is usually represented with a two-dimensional table, these artificial neural networks can by analogy be applied to recommender systems, which are also basically composed of two dimensions (users and elements). Finally, we will analyze the Recurrent Neural Network, which allows the recommendation system using the LSTM and GRU building blocks to "forget" past temporal interactions of the user with the elements, and is therefore useful for recommendations elements whose lifetime is relatively short (e.g. news articles).
Linguistic Editors: Sakellarios, Michalis
Technical Editors: Karatzidis, Dimitrios
Graphic Editors: Symeonidis, Panagiotis
Type: Chapter
Creation Date: 29-05-2023
Item Details:
License: Attribution - NonCommercial - ShareAlike 4.0 International (CC BY-NC-SA 4.0)
Handle http://hdl.handle.net/11419/9578
Bibliographic Reference: Symeonidis, P. (2023). Machine Learning with Neural Nets [Chapter]. In Symeonidis, P. 2023. Intelligent Recommender Systems [Postgraduate textbook]. Kallipos, Open Academic Editions. https://hdl.handle.net/11419/9578
Language: Greek
Is Part of: Intelligent Recommender Systems
Publication Origin: Kallipos, Open Academic Editions