take a number of observations, as he suggests, and let the machine learn the code by determining the coefficients A₀ etc. by simple curvilinear regression. The duration of previous and subsequent signals and the interpretation given to prev…per 'kick' (to use Dr. Selfridge's metaphor) is very small unless the probability of success and failure are equal. If you have a system where there are a vast number of possibilities to be eliminated by rather feckless trial and error, the…
Oliver Selfridge
scientist · 2 mentions across 1 reading
In this course
Oliver Selfridge appears as an early pioneer of machine learning and adaptive systems, referenced here for his work on machines learning through trial-and-error processes and pattern recognition via regression analysis. His "kick" metaphor—suggesting incremental feedback loops where systems adjust based on success and failure outcomes—becomes foundational to understanding how cybernetic systems learn without explicit programming. Though cited only in passing within these excerpts, Selfridge's conceptual framework for probabilistic learning undergirds the course's broader examination of how machines internalize patterns from noisy, uncertain environments.
Mentioned in 1 reading
Appears alongside
People mentioned in the same passages — sorted by co-occurrence weight.