KarlRosaen

1. ML Study
2. Learning Log

Learning Log

Day to day reflections as I work my way through the curriculum. Find related IPython notebooks here.

• Mon, 2/20—Another take on regularization: preferring use of more features

• Tue, 1/17—Practice vectorizing numpy operations, and why KNN stinks at image classification

• Thu, 12/22—Hands-on lecture development for University of Michigan's undergrad ML course and a WIP EM notebook

• Tue, 10/11—Learning features in ANNs and review of Perceptron

• Wed, 10/5—Getting started with Coursera Probabilistic Graphical Models Course

• Tue, 10/4—Getting started with Geoffery Hinton's Coursera Neural Networks class, a nice summary of unsupervised learning

• Wed, 9/28—Regression models with scikit-learn

• Mon, 9/5—Reflections on a summer of learning

• Tue, 8/30—Disappointing improvements using one-hot / binary encoding, improving performance with help of Python profiler

• Mon, 8/29—Creating a confidence interval using Hoeffding's inequality

• Fri, 8/26—A better categorical encoder

• Wed, 8/24—A Wrinkle in Universal Preprocessing of Dataframes

• Tue, 8/23—Probability inequalities applied to bounding expected loss of classifiers

• Fri, 8/19—Machine Learning from a Decision Theoretic perspective with the help of MathMonk

• Mon, 8/15—Multi-stage sampling, Moment Generating Functions

• Thu, 8/11—Conditional Expectation

• Tue, 8/9—Variance of linear combos of R.Vs, Markov's and Chebyshev's inequalities

• Thu, 8/4—A couple of expectation problems and progress on building preprocessing pipelines

• Tue, 8/2—Santosh Venkatesh's Theory of Probability Book, lining up more problems TODO and progress on preprocessing functionality of automatic data science tool

• Thu, 7/28—Study buddy help on a mind blowing probability problem (Binomial where N is Poisson), forging ahead on covariance material

Atom Feed