This 85th episode of Learning Machines 101 discusses formal convergence guarantees for a broad class of machine learning algorithms designed to minimize smooth non-convex objective functions using batch learning methods. In particular, 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. The material in this podcast is designed to provide an overview of Chapter 7 of my new book “Statistical Machine Learning” and is based upon material originally presented in Episode 68 of Learning Machines 101! Check out: www.learningmachines101.com for the show notes!!!
LM101-026: How to Learn Statistical Regularities (Rerun)
LM101-025: How to Build a Lunar Lander Autopilot Learning Machine
LM101-024: How to Use Genetic Algorithms to Breed Learning Machines
LM101-023: How to Build a Deep Learning Machine
LM101-022: How to Learn to Solve Large Constraint Satisfaction Problems
LM101-021: How to Solve Large Complex Constraint Satisfaction Problems (Monte Carlo Markov Chain)
LM101-020: How to Use Nonlinear Machine Learning Software to Make Predictions
LM101-019 (Rerun): How to Enhance Intelligence with a Robotic Body (Embodied Cognition)
LM101-018: Can Computers Think? A Mathematician's Response (Rerun)
LM101-017: How to Decide if a Machine is Artificially Intelligent (Rerun)
LM101-016: How to Analyze and Design Learning Rules using Gradient Descent Methods
LM101-015: How to Build a Machine that Can Learn Anything (The Perceptron)
LM101-014: How to Build a Machine that Can Do Anything (Function Approximation)
LM101-013: How to Use Linear Machine Learning Software to Make Predictions (Linear Regression Software)
LM101-012: How to Evaluate the Ability to Generalize from Experience (Cross-Validation Methods)
LM101-008: How to Represent Beliefs Using Probability Theory
LM101-011: How to Learn About Rare and Unseen Events (Smoothing Probabilistic Laws)
LM101-010: How to Learn Statistical Regularities (MAP and maximum likelihood estimation)
LM101-009: How to Enhance Intelligence with a Robotic Body (Embodied Cognition)
LM101-007: How to Reason About Uncertain Events using Fuzzy Set Theory and Fuzzy Measure Theory
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