Skip to content

Latest commit

 

History

History
31 lines (31 loc) · 967 Bytes

README.md

File metadata and controls

31 lines (31 loc) · 967 Bytes

Machine Learning Algorithms

(Programming Assignments)

  • all algorithms implemented in Python v3.6.4
  • Packaged limited to:
    • Numpy (1.13.1)
    • Scipy (0.19.1)
    • Matplotlib (2.0.2)
    • Pandas (0.20.3)

PA1:

  • K-Nearest Neighbors (KNN)
    • distance functions
    • normalization
  • Decision Trees
    • pruning

PA2:

  • Binary and multiclass classification
  • linear regression

PA3:

  • MultiLayer Perceptron (MLP)
    • Activation Functions (forward and backward): linear, relu, tanh
    • dropout

PA4:

  • K-Means
    • basic K-means clustering algorithm
    • K-means++ algorithm
  • Hidden Markov Model (HMM)
    • forward function, backward function, sequence probability, posterior probability, viterbi algorithm
    • part-of-speech tagging

Comments:

  • PA4_HMM: my implementation of speech tagging achieves a 24.5% improvement in testing accuracy over the class's expected maximum