Mahfuzul Haque

  • Blogs
  • Talks
  • Publications
  • Posters
  • About me
  • Blogs
  • Talks
  • Publications
  • Posters
  • About me

Categories

  • Agile (6)
  • AI and Machine Learning (7)
  • Emotional Intelligence (2)
  • Leadership (8)
  • Personal Development (8)
  • Productivity (1)
  • Reading (5)
  • Scrum and LeSS (5)
  • Software Architecture (9)
  • Software Quaity (1)
  • Team Building (7)
  • User Interface (5)
  • AI and Machine Learning

    Generating labelled training data

    August 8, 2020 /

    Availability of large volume of labelled training data is essential for training your machine learning models, in particular, for training deep neural networks. Some of the options are shown below.

    Read More ...
    Mahfuzul Haque
  • AI and Machine Learning,  Software Architecture

    Scalable machine learning architecture

    July 18, 2020 /

    The conceptual diagram of scalable machine learning architecture.

    Read More ...
    Mahfuzul Haque
  • AI and Machine Learning

    Enabling Machine Learning in a Software Product

    July 27, 2019 /

    The following diagram shows a software product with machine learning (ML) capability enabled in that. If APIs already back the product, then enabling ML means exposing some additional APIs coming…

    Read More ...
    Mahfuzul Haque
  • AI and Machine Learning

    Resilient machine learning systems for health analytics

    January 1, 2017 /

    Tech companies are shifting more towards machine learning or AI-first strategy. What does that mean to them? What does that mean to us? Growing number of aging population and shrinking…

    Read More ...
    Mahfuzul Haque
  • AI and Machine Learning

    Machine learning pipeline for complex video analytics applications

    March 12, 2014 /

    The goal of a video analytics system or application is to generate insights from an observed video stream. In a video analytics system, a continuous stream of video frames is…

    Read More ...
    Mahfuzul Haque
  • AI and Machine Learning

    Pixel-based foreground detector for computer vision applications

    February 12, 2014 /

    A basic pixel-based foreground detector independently maintains a background model for each pixel. Such model is suitable for computer vision applications based on static cameras.

    Read More ...
    Mahfuzul Haque
  • AI and Machine Learning

    How to generate ground truth images?

    December 15, 2013 /

    Ground truth images are essential for the evaluation of object detection or background subtraction techniques. Now what is a ground truth image? Let’s consider a video frame captured using a…

    Read More ...
    Mahfuzul Haque
Mahfuzul Haque © 2021