Classifying Iris flowers with Groovy, Deep Learning, and GraalVM
summary
Uses Groovy to classify the 150-point Iris set with concrete libraries: Weka for decision trees and logistic regression, Smile for KNN, and a Deep Nets/Deep-learning-for-J style neural net that initially misclassifies many samples unless trained longer. Decision tree mislabels 4 versicolor and 5 virginica points; simple logistic drops errors to one. Code compiles with --compile-static and a GraalVM step produces a tiny fast binary; watch for RNG config when building the GraalVM native image.
AI-written summary · about
chapters (6)
- 0:00Introduction and overview
- 3:19What is Groovy?
- 8:54Groovy's value add
- 13:07What is classification?
- 19:28Neural networks overview
- 23:17Groovy with GraalVM
related talks
34mHalf Hour of Flower: Planting the seeds for great Image Quality
51mMachine Learning Exposed Deep and Reinforcement Learning
32mDeploying & serving optimized ML pipelines using graalvm
58mPatterns, Predictions and Programming
21mTransform your web apps with Machine Learning
01h 23mTutorial: A Practical Introduction To Machine Learning
51mMachine Learning with Ruby
24mFrom Model to Microservice - Machine Learning at Scale