Digital Practice is
very interesting.
Digital Practice is the use of digital technology to drive innovation and solve problems.
week 1
This week's lecture introduced what digital media and digital practices are. This is a completely new field for me. This also means that I will face more challenges. I believe I can do it well.
week 2
This week's workshop is quite fun. It taught us how to create a website. Despite encountering many issues such as software compatibility, the task was ultimately completed with the help of tutors and classmates.
week 3
This week, I learned how to extract data from the internet and use it for research projects. Our group had a dispute when selecting the topic. It's difficult for us to narrow down the scope. In the end, our opinions reached a consensus.
week 4
The lecture was very shocking. Data is like a 'clue' when we make decisions. It can help us identify problems and optimize various aspects of work and life. Without data, we are like groping in the dark, making it difficult to make accurate judgments and decisions.
week 5
Data visualization? I think it's about making boring numbers and information more intuitive. Displaying data through charts, images, and other means allows us to quickly identify the problem.
week 6
This week’s lecture focuses on digital perception and ‘Quantified Self’. Explored how technology shapes physical experience and social behaviour. Through case analysis, it reveals how technology affects individuals and society through dataization, monitoring, and gamification.
week 7
This week’s workshop left a deep impression on me. We use Google’s Teachable Machine to train simple models. This is a user-friendly machine learning platform that allows users to train models through simple drag and drop operations without writing code. This makes it easy for even beginners to get started with machine learning. My team and I attempted to train a model to distinguish between different gesture and image categories. We capture real-time gesture actions through cameras, such as waving or raising hands. After the training was completed, we tested the performance of the model in real-time and observed how it made predictions based on input data. Throughout the process, we not only learned how to collect and annotate data, but also personally experienced the significant impact of data quality and diversity on model accuracy. By adjusting the data volume, data category, and training frequency, the team members attempted to improve the performance of the model. In addition, we also discussed the limitations of the model, such as sensitivity to changes in lighting or background complexity. Through this practical session, the seminar deepened our understanding of the fundamental concepts of machine learning, especially the impact of model training and data bias on results, while also triggering further thinking on algorithmic fairness and ethical issues.