Knowledge Graphs, Sequence Translation and Machine Learning on Code

Last week, we organized our 2nd in person MLonCode Meetup in partnership with Neo4j and METIS.

David Mack from Octavian.ai first gave a talk on how to get started with Machine Learning on graphs. He showed a system that is able to take an English language question, convert it into Cypher using a neural network, then run that query against a Neo4j graph database to produce an answer.

You can find David’s slides below and here is a link to the very detailed blog post he wrote on the same topic.

Next up, we had Francesc Campoy giving a talk on Machine Learning on Source Code, walking the audience through the following challenges.

Challenge #1: Data Retrieval

Challenge #2: Data Analysis

Challenge #3: Learning from source Code

Challenge #4: Apply Machine Learning to source code

Francesc showed the audience how source{d} Engine simplifies the process of retrieving code from various git repositories and turning it into language agnostic Abstract Syntax Trees called UASTs that can be analyzed through a flexible and friendly SQL API.

Francesc also introduce source{d} Lookout, a platform helping developers with assisted code review through source code analyzers.

Stay informed about upcoming source{d} events and learning resources by signing up for source{d} bi-weekly newsletter or following us on Twitter.

Learn more about source{d}:

• Watch source{d} Engine in 5 minutes video
• Check out the source{d} Engine repository on GitHub
• Sign up for our upcoming Online Meetup
• Join the source{d} Community Slack