Saturday, February 11, 2017

Udacity Machine Learning Udacity Connect Lesson 01 Syllabus

In-person Udacity Connect Machine Learning Nanodegree syllabus

  • Practice running python from within a Jupyter Notebook (FKA IPython Notebook).

  • Become familiar with importing useful modules and packages, e.g. pandas, numpy, matplotlib.pyplot.

  • Learn about the pandas data structures, including the Series and DataFrame objects.

  • Create a DataFrame object from data in a comma-separated variable (csv) file using pandas.read_csv

  • Index and select data from Series and DataFrame objects using loc and iloc

  • Compute descriptive statistics on a Series or DataFrame, including the mean, the median, and the min & max

  • Explore a public data set found on Kaggle

  • Conduct some exploratory data analysis, and visualize trends in data using matplotlib

Pre Lesson Activities
  • Student Handbook
  • Class schedule and holidays
    • It's an aggressive schedule
  • Logistics
  • Github repo
Lesson 1 in-person activity
  • Meet classmates
  • Meet and greet
  • First lunch is provided. No free lunches in future sessions


Regularization in Machine Learning, Deep Learning

Regularization can prevent overfitting and potentially make algorithm converge faster and more performant. Useful in deep learning tasks, in...