Listen Top Shows Blog

LM101-083: Ch5: How to Use Calculus to Design Learning Machines

LM101-083: Ch5: How to Use Calculus to Design Learning Machines

Update: 2020-08-29

Share

Description

This particular podcast covers the material from Chapter 5 of my new book “Statistical Machine Learning: A unified framework” which is now available! The book chapter shows how matrix calculus is very useful for the analysis and design of both linear and nonlinear learning machines with lots of examples. We discuss how to use the matrix chain rule for deriving deep learning descent algorithms and how it is relevant to software implementations of deep learning algorithms. We also discuss how matrix Taylor series expansions are relevant to machine learning algorithm design and the analysis of generalization performance!!

For additional details check out: www.learningmachines101.com and www.statisticalmachinelearning.com

Comments

In Channel

LM101-086: Ch8: How to Learn the Probability of Infinitely Many Outcomes

LM101-086: Ch8: How to Learn the Probability of Infinitely Many Outcomes

2021-07-2035:29

LM101-085:Ch7:How to Guarantee your Batch Learning Algorithm Converges

LM101-085:Ch7:How to Guarantee your Batch Learning Algorithm Converges

2021-05-2130:51

LM101-084: Ch6: How to Analyze the Behavior of Smart Dynamical Systems

LM101-084: Ch6: How to Analyze the Behavior of Smart Dynamical Systems

2021-01-0533:13

LM101-083: Ch5: How to Use Calculus to Design Learning Machines

LM101-083: Ch5: How to Use Calculus to Design Learning Machines

2020-08-2934:22

LM101-082: Ch4: How to Analyze and Design Linear Machines

LM101-082: Ch4: How to Analyze and Design Linear Machines

2020-07-2329:05

LM101-081: Ch3: How to Define Machine Learning (or at Least Try)

LM101-081: Ch3: How to Define Machine Learning (or at Least Try)

2020-04-0937:20

LM101-080: Ch2: How to Represent Knowledge using Set Theory

LM101-080: Ch2: How to Represent Knowledge using Set Theory

2020-02-2931:43

LM101-079: Ch1: How to View Learning as Risk Minimization

LM101-079: Ch1: How to View Learning as Risk Minimization

2019-12-2426:07

LM101-078: Ch0: How to Become a Machine Learning Expert

LM101-078: Ch0: How to Become a Machine Learning Expert

2019-10-2439:18

LM101-077: How to Choose the Best Model using BIC

LM101-077: How to Choose the Best Model using BIC

2019-05-0224:15

LM101-076: How to Choose the Best Model using AIC and GAIC

LM101-076: How to Choose the Best Model using AIC and GAIC

2019-01-2328:17

LM101-075: Can computers think? A Mathematician's Response (remix)

LM101-075: Can computers think? A Mathematician's Response (remix)

2018-12-1236:26

LM101-074: How to Represent Knowledge using Logical Rules (remix)

LM101-074: How to Represent Knowledge using Logical Rules (remix)

2018-06-3019:22

LM101-073: How to Build a Machine that Learns to Play Checkers (remix)

LM101-073: How to Build a Machine that Learns to Play Checkers (remix)

2018-04-2524:58

LM101-072: Welcome to the Big Artificial Intelligence Magic Show! (Remix of LM101-001 and LM101-002)

LM101-072: Welcome to the Big Artificial Intelligence Magic Show! (Remix of LM101-001 and LM101-002)

2018-03-3122:07

LM101-071: How to Model Common Sense Knowledge using First-Order Logic and Markov Logic Nets

LM101-071: How to Model Common Sense Knowledge using First-Order Logic and Markov Logic Nets

2018-02-2331:40

LM101-070: How to Identify Facial Emotion Expressions in Images Using Stochastic Neighborhood Embedding

LM101-070: How to Identify Facial Emotion Expressions in Images Using Stochastic Neighborhood Embedding

2018-01-3132:04

LM101-069: What Happened at the 2017 Neural Information Processing Systems Conference?

LM101-069: What Happened at the 2017 Neural Information Processing Systems Conference?

2017-12-1623:20

LM101-068: How to Design Automatic Learning Rate Selection for Gradient Descent Type Machine Learning Algorithms

LM101-068: How to Design Automatic Learning Rate Selection for Gradient Descent Type Machine Learning Algorithms

2017-09-2621:49

LM101-067: How to use Expectation Maximization to Learn Constraint Satisfaction Solutions (Rerun)

LM101-067: How to use Expectation Maximization to Learn Constraint Satisfaction Solutions (Rerun)

2017-08-2125:40

00:00

00:00

x

LM101-083: Ch5: How to Use Calculus to Design Learning Machines

LM101-083: Ch5: How to Use Calculus to Design Learning Machines

Richard M. Golden, Ph.D., M.S.E.E., B.S.E.E.