Machine Learning with Ruby
summary
Demo shows a Sinatra web app classifying handwritten digits with 60,000 MNIST images flattened from 28×28 → 784 features and a live SVM trainer that takes three days training in MRI Ruby versus seconds with native libs, yielding about 66.08% on 5,000 test samples for a quick model. Other concrete tools used: gnuplot for linear regression, D3 k‑means on 5,000 points with repeated restarts, live-svm, ai4r, sciruby, scikit‑learn mentions, and Spark/Shark for distributed work.
AI-written summary · about
chapters (32)
- 0:00Intro
- 1:08Exploring the facets of machine learning • Data scientist check list • Practical applications of converse inductive integrals in the context of epsilon
- 2:14Some Background
- 4:25Introduction to Data Mining
- 4:55Depth versus Breadth
- 5:26Types of problems with machine learning answers
- 6:36Supervised versus Unsupervised
- 7:34THUNDERBOLT LABS
- 9:21Required Knowledge
- 9:45Papers
- 10:16Persistence
- 10:56Linear regression
- 20:22Binary classification
- 21:01Support Vector Machines
- 25:32Decision trees
- 34:31Jaccard Coefficient
- 36:00K-Means Clustering
- 37:16JRuby and Mahout
- 38:25Rails on Ruby
- 38:39Fast Math
- 39:35Easy Plotting
- 39:58Integrated Environment
- 42:45Let me dance!
- 44:34Linear Algebra
- 44:45Calculus
- 45:09Coursera ML
- 45:43Wikipedia
- 46:50Find a dataset
- 47:10Find another language
- 48:12Dundas
- 48:23Python Land
- 48:42Shark with Spark
related talks
42mDōmo arigatō, Mr. Roboto: Machine Learning with Ruby
35mIntelligent Ruby: Getting Started with Machine Learning
29mDiscover Machine Learning in Ruby
27mFive machine learning techniques that you can use in your Ruby apps today By Benjamin Curtis Machine learning is everywhere these days
54mMachine Learning explained with Examples
46mPractical Machine Learning and Rails
50mBuilding Intelligent Mobile Apps using Machine Learning
42mLearning Machine Learning