A graph neural network (GNN) is a type of artificial neural network that processes data represented as graphs. It can be applied to various domains such as computer vision and natural language processing. GNNs use pairwise message passing to update node representations by exchanging information with neighboring nodes, and there are different architectures and flavors of message passing. The possibility of defining GNN architectures beyond message passing is still an open research question. Open source libraries like PyTorch Geometric, TensorFlow GNN, and jraph provide implementations of GNNs.

UC Berkeley

Fall 2022

An advanced course dealing with deep networks in the fields of computer vision, language technology, robotics, and control. It delves into the themes of deep learning, model families, and real-world applications. A strong mathematical background in calculus, linear algebra, probability, optimization, and statistical learning is necessary.

No concepts data

+ 14 more conceptsStanford University

Winter 2023

The course focuses on the analysis of large graphs and uses machine learning to gain insights into social, technological, and biological systems. Topics include Graph Neural Networks, influence maximization, disease outbreak detection, and social network analysis.

No concepts data

+ 16 more conceptsStanford University

Spring 2023

This course focuses on data mining and machine learning algorithms for large scale data analysis. The emphasis is on parallel algorithms with tools like MapReduce and Spark. Topics include frequent itemsets, locality sensitive hashing, clustering, link analysis, and large-scale supervised machine learning. Familiarity with Java, Python, basic probability theory, linear algebra, and algorithmic analysis is required.

No concepts data

+ 17 more conceptsBrown University

Spring 2022

Brown University's Deep Learning course acquaints students with the transformative capabilities of deep neural networks in computer vision, NLP, and reinforcement learning. Using the TensorFlow framework, topics like CNNs, RNNs, deepfakes, and reinforcement learning are addressed, with an emphasis on ethical applications and potential societal impacts.

No concepts data

+ 40 more concepts