KEML Knowledge-Enhanced Machine Learning for Reasoning about Ocean Data

Merging data-driven learning and knowledge-based reasoning to answer complex queries about the Blue Amazon.

Leaders: Fabio Cozman and Eduardo Tannuri

Recent breakthroughs in AI have depended on parallel processing of big datasets so as to learn large models through optimization. Further breakthroughs should be possible by judiciously enlisting knowledge representation and planning techniques so as to make learning more efficient, less brittle, and free of biases.

In this context, we investigate conversational agents that can answer high-level questions. Conversations with such agents should include arguments, causes, explanations, and reasoning; it should be possible to conduct a conversation over time and with a purposeful goal, taking into account desires and intentions of the user. Overall, these conversational agents are a laboratory in which to study the connection between data-driven machine learning and knowledge-driven reasoning and planning.

We aim also to develop a framework that will accommodate, with minimal effort, a change in the domain of interest. That is, both the interfacing and reasoning modules, as well services related to the knowledge base, should be general enough that they can be applied to varied domains.

We are developing a conversational expert for a selected domain, so as to test our ideas. We are concentrating most efforts on a large and realistic challenge: to build a useful conversational agent that master all existing knowledge about the Blue Amazon, the vast region in the Atlantic ocean by the Brazilian coastline, rich in biodiversity and energy resources.

Goals

The concrete goal is to develop a framework for conversational agents that can respond to high level requests over time in a particular domain, including questions, arguments, causes, explanations, inferences and plans about specific tasks. We are building a complete conversational expert on the Blue Amazon so as to test and showcase the framework; we expect to develop general tools that are not excessively tied to a particular domain so that the framework can be specialized for any given domain of interest. A broader goal is to investigate how such conversational agents can benefit from data-driven and knowledge-driven techniques simultaneously. 

The BLue Amazon Brain (BLAB) aspires to carry all existing information about the Blue Amazon, both capturing technical expertise in the form of rules and facts and by harvesting data sources available from sensors and from textual information, including scientific papers and newspaper information.

Team

  • Name

    Relevant Information

  • Fabio Gagliardi Cozman
    Full Professor, Universidade de São Paulo
  • Eduardo Aoun Tannuri
    Full Professor, Universidade de São Paulo
  • Anarosa Alves Franco Brandão
    Associate Professor, Universidade de São Paulo
  • Anna Helena Reali Costa
    Full Professor, Universidade de São Paulo
  • Denis Deratani Mauá
    Professor, Universidade de São Paulo
  • Edson Satoshi Gomi
    Professor, Universidade de São Paulo
  • Glauber de Bona
    Professor, Universidade de São Paulo
  • Jaime Simão Sichman
    Full Professor, Universidade de São Paulo
  • Karina Valdivia Delgado
    Professor, Universidade de São Paulo
  • Leliane Nunes de Barros
    Associate Professor, Universidade de São Paulo
  • Renata Wassermann
    Associate Professor, Universidade de São Paulo
  • Sarajane Marques Peres
    Associate Professor, Universidade de São Paulo
  • Valdinei Freire da Silva
    Professor, Universidade de São Paulo
  • Reinaldo Augusto da Costa Bianchi
    Full Professor, Centro Universitário FEI