this paper. Let us place it within the neural network perspective, and particularly that of learning. The area of neural networks has greatly benefited from its unique position at the crossroads of several diverse scientific and engineering disciplines including statistics and probability theory, physics, biology, control and signal processing, information theory, complexity theory, and psychology (see [45]). Neural networks have provided a fertile soil for the infusion (and occasionally confusion) of ideas, as well as a meeting ground for comparing viewpoints, sharing tools, and renovating approaches. It is within the ill-defined boundaries of the field of neural networks that researchers in traditionally distant fields have come to the realization that they have been attacking fundamentally similar optimization problems.

There is a need for frameless guidance systems to help surgeons plan the exact location for incisions, to define the margins of tumors and to precisely identify locations of neighboring critical structures. We have developed an automatic technique for registering clinical data, such as segmented MRI or CT reconstructions, with any view of the patient on the operating table, using a series of registration algorithms, which we demonstrate on the specific example of neurosurgery. The method enables a visual mix of live video of the patient with the segmented 3D MRI or CT model, supporting enhanced reality techniques for planning and guiding neurosurgical procedures, and to interactively view extracranial or intracranial structures non-intrusively. Extensions of the method include image guided biopsies, focused therapeutic procedures and clinical studies involving change detection over time sequences of images. 1 Artificial Intelligence Laboratory, Massachusetts Institute of Tech...

We describe a method of recognizing handwritten digits by fitting generative models that are built from deformable B-splines with Gaussian "ink generators" spaced along the length of the spline. The splines are adjusted using a novel elastic matching procedure based on the Expectation Maximization (EM) algorithm that maximizes the likelihood of the model generating the data. This approach has many advantages. (1) After identifying the model most likely to have generated the data, the system not only produces a classification of the digit but also a rich description of the instantiation parameters which can yield information such as the writing style. (2) During the process of explaining the image, generative models can perform recognition driven segmentation. (3) The method involves a relatively small number of parameters and hence training is relatively easy and fast. (4) Unlike many other recognition schemes it does not rely on some form of pre-normalization of input images, but can ...

The combination of local search heuristics and genetic algorithms is a promising approach for finding nearoptimum solutions to the traveling salesman problem (TSP). In this paper, an approach is presented in which local search techniques are used to find local optima in a given TSP search space, and genetic algorithms are used to search the space of local optima in order to find the global optimum. New genetic operators for realizing the proposed approach are described, and the quality and efficiency of the solutions obtained for a set of symmetric and asymmetric TSP instances are discussed. The results indicate that it is possible to arrive at high quality solutions in reasonable time. I. Introduction In the Traveling Salesman Problem (TSP) [18], [27], a number of cities with distances between them is given and the task is to find the minimum--length closed tour that visits each city once and returns to its starting point. A symmetric TSP (STSP) is one where the distance between any...

Hand-printed digits can be modeled as splines that are governed by about 8 control points. For each known digit, the control points have preferred "home" locations, and deformations of the digit are generated by moving the control points away from their home locations. Images of digits can be produced by placing Gaussian ink generators uniformly along the spline. Real images can be recognized by nding the digit model most likely to have generated the data. For each digit model we use an elastic matching algorithm to minimize an energy function that includes both the deformation energy of the digit model and the log probability that the model would generate the inked pixels in the image. The model with the lowest total energy wins. If a uniform noise process is included in the model of image generation, some of the inked pixels can be rejected as noise as a digit model is tting a poorly segmented image. The digit models learn by modifying the home locations of the control points.

The Self-Organizing Map (SOM) algorithm has been extensively studied and has been applied with considerable success to a wide variety of problems. However, the algorithm is derived from heuristic ideas and this leads to a number of significant limitations. In this paper, we consider the problem of modelling the probability density of data in a space of several dimensions in terms of a smaller number of latent, or hidden, variables. We introduce a novel form of latent variable model, which we call the GTM algorithm (for Generative Topographic Map), which allows general non-linear transformations from latent space to data space, and which is trained using the EM (expectationmaximization) algorithm. Our approach overcomes the limitations of the SOM, while introducing no significant disadvantages. We demonstrate the performance of the GTM algorithm on simulated data from flow diagnostics for a multi-phase oil pipeline. GTM: A Principled Alternative to the Self-Organizing Map 2 1 Introduc...

Abstract not found

: We present and summarize the results from 50-, 100- and 200-city TSP benchmarks presented at the 1989 NIPS post-conference workshop using neural network, elastic net, genetic algorithm and simulated annealing approaches. These results are also compared with a state-of-the-art hybrid approach consisting of greedy solution, simulated annealing, and exhaustive search. 1 carsten@thep.lu.se Background Using neural networks to find approximate solutions to difficult optimization problems is a very attractive prospect. In the original paper [1] 10- and 30-city traveling salesman problems (TSP) were studied with very good results for the N=10 case. For N=30 the authors report on difficulties in finding optimal parameters. In ref. [2] further studies of the Tank-Hopfield approach were made with respect to refinements and extension to larger problem sizes. The authors of ref. [2] find the results discouraging. These and other similar findings have created a negative opinion about the entire...

Parallel genetic algorithms (PGA) use two major modifications compared to the genetic algorithm. Firstly, selection for mating is distributed. Individuals live in a 2-D world. Selection of a mate is done by each individual independently in its neighborhood. Secondly, each individual may improve its fitness during its lifetime by e.g. local hill-climbing. The PGA is totally asynchronous, running with maximal efficiency on MIMD parallel computers. The search strategy of the PGA is based on a small number of intelligent and active individuals, whereas a GA uses a large population of passive individuals. We will show the power of the PGA with two combinatorial problems - the traveling salesman problem and the m graph partitioning problem. In these examples, the PGA has found solutions of very large problems, which are comparable or even better than any other solution found by other heuristics. A comparison between the PGA search strategy and iterated local hill-climbing is made. KEYWORDS ...

Abstract. We describe a novel automatic technique for finding a dense correspondence between a pair of n-dimensional surfaces with arbitrary topologies. This method employs a different formulation than previous correspondence algorithms (such as optical flow) and includes images as a special case. We use this correspondence algorithm to build Morphable Surface Models (an extension of Morphable Models) from examples. We present a method for matching the model to new surfaces and demonstrate their use for analysis, synthesis, and clustering. 1.