Letters to the Editor

In Memorium: Jonathan J. King (1949-1991)

A memorial tribute to AI researcher Jonathan King who died of cancer in 1991.

The computational territory between the linearly summing McCulloch-Pitts neuron and the nonlinear differential equations of Hodgkin & Huxley is relatively sparsely populated. Connectionists use variants of the former and computational neuroscientists struggle with the exploding parameter spaces provided by the latter. However, evidence from biophysical simulations suggests that the voltage transfer properties of synapses, spines and dendritic membranes involve many detailed nonlinear interactions, not just a squashing function at the cell body. Real neurons may indeed be higher-order nets. For the computationally-minded, higher order interactions means, first of all, quadratic terms. This contribution presents a simple learning principle for a binary tree with a logistic/quadratic transfer function at each node. These functions, though highly nested, are shown to be capable of changing their shape in concert. The resulting tree structure receives inputs at its leaves, and outputs an estimate of the probability that the input pattern is a member of one of two classes at the top.

The computational territory between the linearly summing McCulloch-Pitts neuron and the nonlinear differential equations of Hodgkin & Huxley is relatively sparsely populated. Connectionists use variants of the former and computational neuroscientists struggle with the exploding parameter spaces provided by the latter. However, evidence from biophysical simulations suggests that the voltage transfer properties of synapses, spines and dendritic membranes involve many detailed nonlinear interactions, not just a squashing function at the cell body. Real neurons may indeed be higher-order nets. For the computationally-minded, higher order interactions means, first of all, quadratic terms. This contribution presents a simple learning principle for a binary tree with a logistic/quadratic transfer function at each node. These functions, though highly nested, are shown to be capable of changing their shape in concert. The resulting tree structure receives inputs at its leaves, and outputs an estimate of the probability that the input pattern is a member of one of two classes at the top.

Arthur Samuel (1901-1990) was a pioneer of artificial intelligence research. From 1949 through the late 1960s, he did the best work in making computers learn from their expe-rience. His vehicle for this work was the game of checkers.

From 1949 through the late required to have his research more didn't finish 1960s, he did the best work in making vigorously followed up on. He was the computers learn from their experience. Programs for playing games often and what would be required to In 1949, Samuel joined IBM's fill the role in artificial intelligence reach human-level intelligence. Poughkeepsie Laboratory, where he research that the fruit fly Drosophila Samuel's papers on machine learning worked on IBM's first stored program plays in genetics. Drosophilae are are still worth studying.

Letters to the Editor.