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…In speed and information theory, I really consider that speed in the classic sense of computation is so completely irrelevant to this problem - the number of binary operations one does a second - that it does not interest me very much thoug…
Christopher Strachey
scientist · 2 mentions across 1 reading
In this course
Christopher Strachey was a pioneering computer scientist and programmer who worked on early machine learning and adaptive systems in the 1950s-60s, contributing foundational ideas about how machines could learn patterns from data through regression and coefficient determination. The readings invoke his work to argue that computational speed in the traditional sense (binary operations per second) misses the point of what matters in information processing and learning systems. His insight that machines could determine parameters automatically rather than through explicit programming becomes crucial to the course's discussion of how feedback loops and adaptive systems function outside classical computational paradigms.
Mentioned in 1 reading
Appears alongside
People mentioned in the same passages — sorted by co-occurrence weight.