27 min listen
LM101-014: How to Build a Machine that Can Do Anything (Function Approximation)
LM101-014: How to Build a Machine that Can Do Anything (Function Approximation)
ratings:
Length:
33 minutes
Released:
Oct 13, 2014
Format:
Podcast episode
Description
In this episode, we discuss the problem of how to build a machine that can do anything! Or more specifically, given a set of input patterns to the machine and a set of desired output patterns for those input patterns we would like to build a machine that can generate the specified output pattern for a given input pattern. This problem may be interpreted as an example of solving a supervised learning problem. Checkout the shownotes at: www.learningmachines101.com for a transcript of this show and free machine learning software!
Released:
Oct 13, 2014
Format:
Podcast episode
Titles in the series (85)
LM101-022: How to Learn to Solve Large Constraint Satisfaction Problems: In this episode we discuss how to learn to solve constraint satisfaction inference problems. by Learning Machines 101