K-Nearest Neighbor (k-NN) & Artificial Neural Networks

Overview/Description
Target Audience
Prerequisites
Expected Duration
Lesson Objectives
Course Number
Expertise Level

---

Overview/Description
Choosing the appropriate technique to deliver confident predictions can be challenging for analysts. Explore algorithms used for predictive analytics, including the K-Nearest Neighbor (k-NN) algorithm and artificial neural network modeling.

Target Audience
All individuals who are new to predictive analytics and wish to use it to optimize their business performance; business leaders; analysts; marketing, sales, software, and IT professionals who want to add predictive analytics to their skill set; and decision makers of any kind

Prerequisites
None

Expected Duration (hours)
0.8

Lesson Objectives

K-Nearest Neighbor (k-NN) & Artificial Neural Networks

start the course

recognize features of the k-NN algorithm

recognize distance and weighted distance measures

recognize proximity measures for non-numeric attributes

implement the k-NN algorithm

identify key features of artificial neural networks

recognize steps and considerations to building artificial neural networks

recognize the purpose of nonlinear activation functions and methods to find the global minimum SSE

recognize important parameters for artificial neural networks

implement an artificial neural network

Course Number:
df_prma_a09_it_enus

Expertise Level
Intermediate