Neural Network Madness: Quick Overview and Excellent Resource
It seems like technical news is always talking about how neural network models are helping predict this or detect that. For example, a recent article came out describing how MIT researchers have developed a model that can identify 97% of COVID-19 just by a person’s cough—even in asymptomatic people. When you first hear it without any background, immediately, it sounds like something that is way beyond what you can comprehend. Why? Because it sounds like it has something to do with the brain and that sounds complicated.
Going Through the Machine Learning Motion
After completing my third project, I have learned a lot about training different models with my processed data, using those models to make predictions, and evaluating their performance; however, what I failed to fully grasp is how some of these models were actually doing all these amazing calculations in the background. So, I decided to do further investigation into 3 of the models without going too deeply into the math. My goal is to give simple descriptions—after all, the math is where most of our eyes glaze over.
Model Selection Process
Intimidation Factor
At first, creating a model that can not only predict outcomes but can do it well is intimidating to a novice data scientist. Essentially, you are bringing an abstract concept to life that will impact the world whether that just be in a project you will present to an instructor for a Data Science course through Flatiron, or at the expense of a corporate budget.
What an Adventure!
My first project through Flatiron School’s Data Science course is done, and I am extremely proud of not only with what I have done, but what I have learned!