Jianhao Ma's IMA Blog

 A6: Quick Draw! About Quick Draw Data Set Quick Draw is a representative machine learning & data collection project, it shows an ideal design model for public machine learning and data set projects.  It's simply designed to be engaging and accessible. And such accessibility profligates the data collection progress. It uses the classification model trained with collected data as a feedback to reward participants.  Although there are several potential problems with the dataset such as latent bias, I still found it very helpful for beginners. Both the doodle and the label are small objects (compared to other visual machine learning projects), therefore are easy and fast to process. It makes ambitious attempts possible for machine learning learners.  DoodleNet p5 Sketch https://editor.p5js.org/roger1mjh/sketches/kPVq2Prxl For this week's homework, I worked on the "two canvases" template. My idea is to visually represent and store the "labels", "confide...

Exploring Datasets and Practice on 311 World Happiness Report I've seen other datasets from Gallup World Poll before and was interested in how it quantifies happiness and its parameters. Here's the details of this dataset:     Collector/contributor:   United Nations     Purpose : Happiness Indicators to inform government's decision makings     Collection Method:  Data are collected from Gallup World Poll     Dimensions:  156 lines(countries), 12 columns The dataset quantifies happiness of citizens from different countries from a macro perspectives. It combines individual polls and objective statistics. It's convenient to use machine learning and do a regression to estimate the correlation between Happiness and each parameters(GDP, life expectancy, etc..) 311 p5 sketch exercise https://editor.p5js.org/roger1mjh/sketches/ZG2BkJS07 Originally I want to make some edits on the existed code to conduct a different use of the simplifi...

 Image Transfer on P5 Response to Dr. Fiebrink's Speech: There's one part in this speech that intrigues me the most, which is using Machine Learning in creative works does not need to be smart and delicate. It is OK to be dumb and funny, because that's what an unmatured technology genuinely looks like, and it can still be creative. The Edges to Cat example is so fun to play with that I'm kind of addict to it.  Attempt to do Image Transfer on P5 with Pose Regression I watched the videos posted and was most interested in the pose regression example. But the RGB value shift looks not "machine learningly" enough, because it's possible to make some similar project without neural network. Therefore I tried to make one with image transfer. Firstly, I need to load image in data format in P5. I decided to try pixels first, because they retrieve and store image data directly. Then I console logged the "pixels" object in draw, to test out how much the data ...

 A3: Applications of Machine Learning models Jianhao Ma Response to PoseNet's Data & Model Biography To be more specific the biography provided is for MobileNet. However, I did learn something about PoseNet because it's the sub model of MobileNet.  One important thing I noticed is that the model is optimized for devices with limited performance, ones that can be easily embedded and require less power. Therefore, it can be applied to outdoor activities in daily life scenarios. Moreover, PoseNet does a really good job in inspecting and classifying people's poses and gestures. All of the followings inspired me to make my project this week. Have A Safe Ride My intention is to make a demo of an application that detects motorcycle hand signals.  My plan for the application is to embed them in auto-driving and safety technologies on automobiles. It enables cars to recognize the hand signals of bikers in front of them and responses safely based on that. I built my project on ...

2A: Excavating AI, Teachable Machine Project Jianhao Ma Moral Machines The reading "Excavating AI" brings up an idea that the tasks of training AI should not just be making them smarter, but to apply political consideration and moral standard as well, especially when related to people. I would not care about such idea years ago, because I thought that technical breakthroughs is the one and foremost priority in emerging technology industries, why bother? However, when the application of machine learning started entering our lives, I changed my mind. Everyday, there are many information processed/filtered by machine learning tools being fed to us, textual or non textual. They could be the advertisement you watch on social media, the pop-up news on your phone. In other words, many of the lower products of machine learning are mediums. Therefore, they have the inherent nature of being political biased and ideologically influential. The fantasy that "technologies should be un...

Week2: ImageNet and MobileNet  Jianhao Ma ImageNet My initial impression with ImageNet is about how slow it is. But I thought that makes sense regarding it is a non-profitable research project with a huge dataset. I tried to find how big the dataset is and figured out that the statistics hasn't been updated for 10 years. Later I realized that not only the search engine lacks consistency, the tree view is also taking forever.  As I browsed through ImageNet, I started to have a sense that it's one of those early Image Classification project that's been forbidden by time. Can't neglect that there are many privacy concerns, especially under "person" synsets. I think that they would have be more careful when selecting synsets of illegal occupations and minority groups if it's a recent project. But I wouldn't blame that on ImageNet because that's the common theme of fabricating any datasets with all resources on the Internet. It's too much works for ...