Machine Learning with Scratch Block-coding

Machine Learning with Scratch Block-coding

2023-02-16T23:53:18+09:00 Feb 16, 2023|Tinker Stories|0 Comments

Machine Learning is a branch of artificial intelligence based on the idea that systems can learn from data, identify patterns and make decisions with minimal human intervention.

Simply put, Machine Learning enables IT systems to recognize patterns on the basis of existing algorithms and data sets and to develop adequate solution concepts.

The Moraa used the popular Scratch platform to learn Machine Learning due to its simplified and attractive User Interface (UI) and ease of use. Subsequently, she needed to focus on learning key concepts that relate to Machine Learning.

In this field, traditional programming rules do not operate; very high volumes of data can teach algorithms to create better computing models.

Some of the game-changing concepts Moraa learnt during the term were:

  1. Text recognition: Moraa trained a machine learning model (a set of assumptions about the underlying nature of the data to be trained for) to recognize the meaning of instructions. She used a virtual assistant that responded to commands. Practically, this technology can be seen used by virtual assistants like chatbots. Users can simply text within a service like a website and have the platform execute their commands.
  1. Sentiment Analysis: Moraa learnt how to supervise their machine learning models to recognize compliments and insults by typing examples of kind statements, mean statements and neutral statements. She created a character in Scratch that reacts to her sentiments. This technology can be seen as widely used by social media giants such as Twitter and Facebook to enhance accurate and cordial online interactions. YouTube, on the other hand, can moderate user comments.
  1. Object recognition in pictures: This technology is widely used online by services such as Instagram and Facebook to improve user experience where people in photos can automatically be identified and easily tagged. In class, Moraa made cards with different symbols whose pictures were taken and a machine learning model trained to recognize the objects in them. The Machine Learning model matches the objects based on its pool of analyzed data.
  1. Handwriting recognition: Moraa learnt how computers can be trained to recognize handwriting. The use of optical character recognition technique is normally used to automate this kind of task. In the real world, smartphones such as the Galaxy Note by Samsung use stylus pens to digitize any writing made on its surface. This technology is very useful and needed by people in various professional fields.

Leave A Comment