Supervised Learning
VLSI Implementation of TInMANN
Melton, Matt, Phan, Tan, Reeves, Doug, Bout, Dave Van den
A massively parallel, all-digital, stochastic architecture - TlnMAN N - is described which performs competitive and Kohonen types of learning. A VLSI design is shown for a TlnMANN neuron which fits within a small, inexpensive MOSIS TinyChip frame, yet which can be used to build larger networks of several hundred neurons. The neuron operates at a speed of 15 MHz which allows the network to process 290,000 training examples per second. Use of level sensitive scan logic provides the chip with 100% fault coverage, permitting very reliable neural systems to be built.
Extensions of a Theory of Networks for Approximation and Learning: Outliers and Negative Examples
Girosi, Federico, Poggio, Tomaso, Caprile, Bruno
Learning an input-output mapping from a set of examples can be regarded as synthesizing an approximation of a multidimensional function.
VLSI Implementation of TInMANN
Melton, Matt, Phan, Tan, Reeves, Doug, Bout, Dave Van den
A massively parallel, all-digital, stochastic architecture - TlnMAN N - is described which performs competitive and Kohonen types of learning. A VLSI design is shown for a TlnMANN neuron which fits within a small, inexpensive MOSIS TinyChip frame, yet which can be used to build larger networks of several hundred neurons. The neuron operates at a speed of 15 MHz which allows the network to process 290,000 training examples per second. Use of level sensitive scan logic provides the chip with 100% fault coverage, permitting very reliable neural systems to be built.
Extensions of a Theory of Networks for Approximation and Learning: Outliers and Negative Examples
Girosi, Federico, Poggio, Tomaso, Caprile, Bruno
Bruno Caprile I.R.S.T. Povo, Italy, 38050 Learning an input-output mapping from a set of examples can be regarded as synthesizing an approximation of a multidimensional function.
Generalization as Search
"The purpose of this paper is to compare various approaches to generalization in terms of a single framework. Toward this end, generalization is cast as a search problem, and alternative methods for generalization are characterized in terms of the search strategies that they employ. This characterization uncovers similarities among approaches, and leads to a comparison of relative capabilities and computational complexities of alternative approaches. The characterization allows a precise comparison of systems that utilize different representations for learned generalizations."Artificial Intelligence, 18 (2), 203-26.