Learnings of a Maker LU

The more dimensions we have, the more data we need.

#ML, #Machinelearning, #LearnBuildShare, #coder, #programming, #learning, #humanlearning #IamaHumanLearningMachineLearning #SciJoyML

I was cursed. I had to explore what higher dimensional spheres and cubes looked like. Here is a playlist of more visual explanations. I’ll get back to regular ML on day 7.

https://www.youtube.com/playlist?list=PL0XpKwCBES4NH5d_X6Xp8QE-On6PoT98S

#ML, #Machinelearning, #LearnBuildShare, #coder, #programming, #learning, #humanlearning #IamaHumanLearningMachineLearning #SciJoyML

I dove down a rabbit hole and discovered that Bayesian methods cracked codes, solved medical mysteries, predicted elections, found ships, determined nuclear safety, and much more. I also learned there is a giant math war between Frequentists and Bayesians.

#ML, #Machinelearning, #LearnBuildShare, #coder, #programming, #learning, #humanlearning #IamaHumanLearningMachineLearning #SciJoyML

The ROC curve helps determine an algorithms accuracy. We can chose to make our algorithm more or less risk-adverse.

#ML, #Machinelearning, #LearnBuildShare, #coder, #programming, #learning, #humanlearning #IamaHumanLearningMachineLearning #SciJoyML

We take a look at the loss matrix and the confusion matrix. Using Bayes, we can determine if our rover should drive over rocks or avoid them. You can adjust the numbers and test out your own theories with this google sheet — https://docs.google.com/spreadsheets/d/1t8MnTQpOy33vlQXZILZyInHDDJvs8yAetwNM04OcRt4/edit?usp=sharing

#100DaysOfMLCode #ML, #Machinelearning, #LearnBuildShare, #coder, #programming, #learning, #humanlearning #IamaHumanLearningMachineLearning #SciJoyML

Overview of Naive Bayes Algorithm. Sorry the audio quality is off. Ran out of time to redo. I also post daily videos and blog posts. I'll do better tomorrow. Thanks for listening!