An intro to Knowledge Graphs, based on our knowledge of Graph Neural Networks. A simple example provides an easy pathway to Knowledge Graphs and training of Knowledge Graphs (AI). Knowledge graphs (KG) are data structures that store information about different entities (nodes) and their relations (edges). A common approach of using KG in various machine learning tasks is to compute knowledge graph embeddings. A knowledge graph (KG) is a directed heterogeneous multigraph whose node and relation types have domain-specific semantics. KG allow us to encode the knowledge into a form that is human interpretable and amenable to automated analysis and inference. Two models for Knowledge Graph Embeddings are presented and expained: TransE and TransR. 00:00 Remember word embedding? 01:53 Knowledge graph embedding 03:18 Simple knowledge graph 06:52 Key idea 08:50 Closeness 12:20 TransE explained 13:18 Knowledge graph embeddings 15:18 TransR explained #knowledgegraph #embedding #Intro2KnowledgeGraphs #graphs #neuralnetworks #ai #machinelearningwithpython #convolutionalneuralnetwork #jupyterlab #dgl #word2vec