This 68th episode of Learning Machines 101 discusses a broad class of unsupervised, supervised, and reinforcement machine learning algorithms which iteratively update their parameter vector by adding a perturbation based upon all of the training data. This process is repeated, making a perturbation of the parameter vector based upon all of the training data until a parameter vector is generated which exhibits improved predictive performance. The magnitude of the perturbation at each learning iteration is called the “stepsize” or “learning rate” and the identity of the perturbation vector is called the “search direction”. Simple mathematical formulas are presented based upon research from the late 1960s by Philip Wolfe and G. Zoutendijk that ensure convergence of the generated sequence of parameter vectors. These formulas may be used as the basis for the design of artificially intelligent smart automatic learning rate selection algorithms. For more information, please visit the official website:
www.learningmachines101.com
LM101-086: Ch8: How to Learn the Probability of Infinitely Many Outcomes
LM101-085:Ch7:How to Guarantee your Batch Learning Algorithm Converges
LM101-084: Ch6: How to Analyze the Behavior of Smart Dynamical Systems
LM101-083: Ch5: How to Use Calculus to Design Learning Machines
LM101-082: Ch4: How to Analyze and Design Linear Machines
LM101-081: Ch3: How to Define Machine Learning (or at Least Try)
LM101-080: Ch2: How to Represent Knowledge using Set Theory
LM101-079: Ch1: How to View Learning as Risk Minimization
LM101-078: Ch0: How to Become a Machine Learning Expert
LM101-077: How to Choose the Best Model using BIC
LM101-076: How to Choose the Best Model using AIC and GAIC
LM101-075: Can computers think? A Mathematician's Response (remix)
LM101-074: How to Represent Knowledge using Logical Rules (remix)
LM101-073: How to Build a Machine that Learns to Play Checkers (remix)
LM101-072: Welcome to the Big Artificial Intelligence Magic Show! (Remix of LM101-001 and LM101-002)
LM101-071: How to Model Common Sense Knowledge using First-Order Logic and Markov Logic Nets
LM101-070: How to Identify Facial Emotion Expressions in Images Using Stochastic Neighborhood Embedding
LM101-069: What Happened at the 2017 Neural Information Processing Systems Conference?
LM101-067: How to use Expectation Maximization to Learn Constraint Satisfaction Solutions (Rerun)
Create your
podcast in
minutes
It is Free
Insight Story: Tech Trends Unpacked
Zero-Shot
Fast Forward by Tomorrow Unlocked: Tech past, tech future
The Unbelivable Truth - Series 1 - 26 including specials and pilot
A Prairie Home Companion: News from Lake Wobegon