SSL and Delayed Labelling
Presentation, University of Waikato, Online
Guest Lecture concerning SSL and Delayed Labelling for undergraduate students at the University of Waikato (Hamilton, NZ)
Talks and presentations
Machine Learning for Streaming Data
Presentation, China University of Mining and Technology, Online
Guest Lecture concerning Machine Learning for Streaming Data for graduate students at China University of Mining and Technology
Concept Drift Detection and Applications
Presentation, Stats NZ data science seminar, Online
Guest Lecture concerning Concept Drift Detection and Applications for data scientists from Stats NZ
Semi-Supervised Learning for Delayed Partially Labelled Data Streams
Tutorial, AIRA 2022, University of Canterbury, New Zealand
Presentation at the Artificial Intelligence Researchers Association of New Zealand meetup. Conference website My presentation video
Machine Learning for Streaming Data
Presentation, Michigan Technological University, Online
Guest Lecture entitled “Machine Learning for Streaming Data” for undergrad and graduate students at Michigan Technological University (USA)
Learning for Delayed Partially Labelled Data Streams
Presentation, ICDM workshop (IncrLearn 2021), Auckland, New Zealand
Keynote at the IncrLearn workshop in ICDM 2021. Program: https://incrlearn.sciencesconf.org/resource/page/id/7 Slides: https://incrlearn.sciencesconf.org/data/Gomes_IncrLearn21.pdf
Introduction to MOA
Presentation, International WEKA user conference, Hamilton, New Zealand
Talk at the International WEKA user conference introducing MOA Program website My presentation video
Aprendizagem de Máquina para fluxos de dados contínuos (Machine learning for continuous data streams)
Presentation, Itau Data Science Talk, Online
Invited talk at the Itau data science meeting.
Machine Learning for Streaming Data
Presentation, Cardiff University seminar, Online
Invited talk at the Joint Machine Learning Seminar hosted collaboratively by Cardiff University and the University of Waikato
Semi-Supervised Learning for Delayed Partially Labelled Data Streams
Presentation, UoW Machine Learning Seminar, Online
Presentation at the machine learning seminar series at the University of Waikato
Machine Learning for Data Streams Master Class
Presentation, ENZ Latin America Masterclass, Online
Guest lecture for the Latin America Masterclasses organised by the New Zealand Education (ENZ)
Machine learning for streaming data: state of the art, challenges, and opportunities
Tutorial, AIRA 2021, Hobbiton, New Zealand
Presentation at the first Artificial Intelligence Researchers Association of New Zealand meetup. Conference website My presentation video
Machine learning for data streams with scikit-multiflow
Tutorial, International Joint Conference on Artificial Intelligence, Yokohama, Japan
In this tutorial we introduced attendees to data stream mining procedures and examples of big data stream mining applications with examples using the scikit-multiflow. The tutorial was scheduled for IJCAI 2020 but ended up being presented early 2021 due to the pandemic. Website: https://streamlearningtutorial2020.netlify.app/
Lecture at the IOT Stream Data Mining course
Lecture, Telecom Paris, Paris, France
Lecture at the IOT Stream Data Mining course (Paris, France) as part of the Data and Knowledge 2nd year Master Program of Université Paris Saclay 2019-2020.
Streaming Random Patches for Evolving Data Stream Classification
Seminar, INESC-TEC, Porto, Portugal
Presented the paper “Streaming Random Patches for Evolving Data Stream Classification.”
Machine learning for streaming data: Practical insights
Talk, Javits Center, New York, USA
In many domains, data is generated at a fast pace. A clear example is the Internet of Things (IoT) applications, where connected sensors yield large amount of data in short periods. To build predictive models from this data, you need to either settle for traditional offline learning or attempt to learn from the data incrementally. A significant setback with the offline learning approach is that it’s slow to react to changes in the domain, and these changes can have a catastrophic impact on the model predictive performance, since the patterns in which the model was trained on are no longer valid. An online approach where the model is trained incrementally can potentially fix this; however, the untold story is that the existing challenges for offline learning are still present (and are even maximized) when processing the data online. These challenges include, but are not limited to, raw data preprocessing, efficient incremental updates to models, algorithms to detect changes and react to them, and dealing with lots of unlabeled and delayed-labeled data.
Streaming Random Forest Learning in Spark and StreamDM
Talk, ExCel London, London, UK
We present how to build random forest models from streaming data. This is achieved by training, predicting and adapting the model in real-time with evolving data streams. The implementation is on the open source library StreamDM, built on top of Apache Spark.
Machine learning for nonstationary streaming data using Structured Streaming and StreamDM
Talk, Javits Center, New York, USA
The main difference between batch machine learning implementations in Spark (MLlib and Spark ML) and StreamDM is that the latter focus on algorithms that can be trained and adapted incrementally. This can be a huge advantage in some domains as it enables automatically updating the learning models. StreamDM is currently under development by Huawei Noah’s Ark Lab and Télécom ParisTech.
Big Data Stream Mining using Spark Streaming
Tutorial, Croke Park Conference Centre, Dublin, Ireland
The volume of data is rapidly increasing due to the development of the technology of information and communication. This data comes mostly in the form of streams. Learning from this ever-growing amount of data requires flexible learning models that self-adapt over time. In addition, these models must take into account many constraints: (pseudo) real-time processing, high-velocity, and dynamic multi-form change such as concept drift and novelty. The tutorial was combined with a workshop on the same topic.
Machine Learning for Spark Streaming with StreamDM
Tutorial, Barra da Tijuca Beach Windsor, Rio de Janeiro, Brazil
The main goal of this tutorial is to introduce attendees to big data stream mining theory and practice. We will use the StreamDM framework to illustrate concepts and also to demonstrate how data stream mining pipelines can be deployed using StreamDM.
StreamDM: Advanced data science with Spark Streaming
Tutorial, ExCel London, London, UK
An overview of StreamDM, a real-time analytics open source software library built on top of Spark Streaming, developed at Huawei’s Noah’s Ark Lab and Télécom ParisTech.
Ensemble Learning for Evolving Data Streams
Talk, Harbin Institute of Technology, Shenzhen, China
Invited talk at the Harbin Institute of Technology (HIT) (Shenzhen, China): Ensemble Learning for Evolving Data Streams.