Theoretical Foundations of the Potential Function Method in Pattern Recognition Learning

By M. Aizerman. 1964

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Word Representations via Gaussian Embedding (2014, background): “This paper advocates moving beyond vector point representations to potential functions (Aizerman et al., 1964), or continuous densities in latent space.”
Fastfood: Approximate Kernel Expansions in Loglinear Time (2014, methodology): “This idea was ﬁrst used by Aizerman et al. (1964) to show nonlinear separation.”
Kernel methods in machine learning (2007, neutral): “[1] used kernels as a tool in a convergence proof, allowing them to apply the Perceptron convergence theorem to their class of potential function algorithms.”
Latent Semantic Kernels (2001, background): “Though the idea of using a kernel defined feature space is not new (Aizerman et al., 1964), it is only recently that its full potential has begun to be realised.”
SVM-Based Multimodal Classification of Activities of Daily Living in Health Smart Homes: Sensors, Algorithms, and First Experimental Results (2010, background): “These sensors detect all movements in their area they cover and send a signal each time a movement is detected.”
Theory of classification : a survey of some recent advances (2005, methodology): “Kernel methods were pioneered by Aizerman, Braverman, and Rozonoer [2] [3] [4] [5], Vapnik and Lerner [228], Bashkirov, Braverman, and Muchnik [31], Vapnik and Chervonenkis [233], and Specht [203].”
On the generalization ability of on-line learning algorithms (2001, methodology): “We begin by considering the classical Perceptron algorithm [35], [36], [37] in its dual kernel form, as investigated in, e.g., [27], [ 38 ].”
Adaptive computation and machine learning (1998, methodology): “Of course, the kernel Perceptron algorithm already given by Aizerman et al. [1964] could straightforwardly succeed to do so using second-degree polynomial kernels. The margin bound for the Perceptron algorithm was proven by Novikoff [1962] and is one of the first results in learning theory. The leav”