Tony Martinez

Followers

Following

Co-authors

Public Views

Interests

Uploads

Papers by Tony Martinez

The robustness of majority voting compared to filtering misclassified instances in supervised classification tasks

Artificial Intelligence Review, 2016

Using Classifier diversity to handle label noise

2015 International Joint Conference on Neural Networks (IJCNN), 2015

Wagging: A learning approach which allows single layer perceptrons to outperform more complex learni

Abstract: Despite the well known inability of single layer perceptrons (SLPs) to learn arbitrary ... more

Multiple output relaxation machine learning model

On the Pseudo Multilayer Learning of Backpropagation

Rosenblatt&amp;amp;amp;amp;amp;amp;#39;s convergence theorem for the simple perceptron initia... more Rosenblatt&amp;amp;amp;amp;amp;amp;#39;s convergence theorem for the simple perceptron initiated much excitement about iterative weight modifying neural networks. However, this convergence only holds for the class of linearly separable functions, which is vanishingly small compared to arbitrary functions. With multilayer networks of nonlinear units it is possible, though not guaranteed, to solve arbitrary functions. Backpropagation is a method of training multilayer networks

Efficient Construction of Networks for Learned Representations with General to Specific Relationships

Intelligent Systems Third Golden West International Conference, 1995

Machine learning systems often represent concepts or rules as sets of attribute-value pairs. Many... more

Neural network applicability: Classifying the problem space

Proceedings of the IASTED International Symposium …, 1989

The tremendous current effort to propose neurally inspired methods of computation forces closer s... more

A VLSI implementation of a parallel, self-organizing learning model

Proceedings of the 12th IAPR International Conference on Pattern Recognition (Cat. No.94CH3440-5), 2000

This paper presents a VLSI implementation of the Priority Adaptive Self-organizing Concurrent Sys... more This paper presents a VLSI implementation of the Priority Adaptive Self-organizing Concurrent System (PASOCS) learning model that is built using a multichip module (MCM) substrate. Many current hardware implementations of neural network learning models are direct implementations of classical neural network structures-a large number of sample computing nodes connected by a dense number of weighted links. PASOCS is one of a class of ASOCS (Adaptive Self-Organizing Concurrent System) connectionist models whose overall goal is the same as classical neural networks models, but whose functional mechanisms differ significantly. This model has potential application in areas such as pattern recognition, ro botics, logical inference, and dynamic control.

Download

A multi-chip module implementation of a neural network

Proceedings of IEEE Multi-Chip Module Conference (MCMC-94), 2000

The requirement for dense interconnect in artificial neural network systems has led researchers t... more The requirement for dense interconnect in artificial neural network systems has led researchers to seek high-density interconnect technologies. This paper reports an implementation using multi-chip modules (MCMs) as the interconnect medium. The specific system described is a self-organizing, parallel, and dynamic learning model which requires a dense interconnect technology for effective implementation; this requirement is fulfilled by exploiting MCM technology. The ideas presented in this paper regarding an MCM implementation of artificial neural networks are versatile and can be adapted to apply to other neural network and connectionist models. 20 0-8186-5560-7B4 $03.00 0 1994 JEEE

Download

Generating a novel sort algorithm using Reinforcement Programming

Ieee Congress on Evolutionary Computation, 2010

Reinforcement Programming (RP) is a new approach to automatically generating algorithms, that use... more Reinforcement Programming (RP) is a new approach to automatically generating algorithms, that uses reinforcement learning techniques. This paper describes the RP approach and gives results of experiments using RP to generate a generalized, in-place, iterative sort algorithm. The RP approach improves on earlier results that that use genetic programming (GP). The resulting algorithm is a novel algorithm that is more efficient than comparable sorting routines. RP learns the sort in fewer iterations than GP and with fewer resources. Results establish interesting empirical bounds on learning the sort algorithm: A list of size 4 is sufficient to learn the generalized sort algorithm. The training set only requires one element and learning took less than 200,000 iterations. RP has also been used to generate three binary addition algorithms: a full adder, a binary incrementer, and a binary adder.

Download

Using Evolutionary Computation to Generate Training Set Data for Neural Networks

Download

Hierarchical based sequencing machine learning model

Reduction Techniques for Exemplar-Based Learning Algorithms

Exemplar-based learning algorithms are often faced with the problem of deciding which instances o... more Exemplar-based learning algorithms are often faced with the problem of deciding which instances or other exemplars to store for use during generalization. Storing too many exemplars can result in large memory requirements and slow execution speed, and can cause an oversensitivity to noise. This paper has two main purposes. First, it provides a survey of existing algorithms used to reduce the number of exemplars retained in exemplar-based learning models. Second, it proposes six new reduction algorithms called DROP1-5 and DEL that can be used to prune instances from the concept description. These algorithms and 10 algorithms from the survey are compared on 31 datasets. Of those algorithms that provide substantial storage reduction, the DROP algorithms have the highest generalization accuracy in these experiments, especially in the presence of noise.

Download

Initializing the Amplitude Distribution of a Quantum State

Found Phys Lett, 1999

To date, quantum computational algorithms have operated on a superposition of all basis states of... more To date, quantum computational algorithms have operated on a superposition of all basis states of a quantum system. Typically, this is because it is assumed that some function f is known and implementable as a unitary evolution. However, what if only some points of the function f are known? It then becomes important to be able to encode only the knowledge that we have about f. This paper presents an algorithm that requires a polynomial number of elementary operations for initializing a quantum system to represent only the m known points of a function f. PACS numbers: 03.67.Lx, 03.67.-a, 89.80.+h, 03.65.Bz

Download

Instance weighted learning machine learning model

A Transformation For Implementing Neural Networks With Localist Properties

Ijis, 1995

Time Series Gene Expression Prediction using Neural Networks with Hidden Layers

by Michael R Smith, Tony Martinez, and Mark Clement

Proceedings of the 7th Annual Biotechnology and Bioinformatics Symposium (BIOT 2010), Oct 2010

Download

AA1: A Dynamic Incremental Network That Learns By Discrimination

Abstract An incremental learning algorithm for a special class of self-organising, dynamic networ... more Abstract An incremental learning algorithm for a special class of self-organising, dynamic networks is presented. Learning is e ected by adapting both the function performed by the nodes and the overall network topology, so that the network grows (or shrinks) over time to t the problem. Convergence is guaranteed on any arbitrary Boolean dataset and empirical generalisation results demonstrate promise.

***WITHDRAWN PATENT AS PER THE LATEST USPTO WITHDRAWN LIST***Instance weighted learning machine learning model

Becoming More Robust to Label Noise with Classifier Diversity

It is widely known in the machine learning community that class noise can be (and often is) detri... more It is widely known in the machine learning community that class noise can be (and often is) detrimental to inducing a model of the data. Many current approaches use a single, often biased, measurement to determine if an instance is noisy. A biased measure may work well on certain data sets, but it can also be less effective on a broader set of data sets. In this paper, we present noise identification using classifier diversity (NICD) -- a method for deriving a less biased noise measurement and integrating it into the learning process. To lessen the bias of the noise measure, NICD selects a diverse set of classifiers (based on their predictions of novel instances) to determine which instances are noisy. We examine NICD as a technique for filtering, instance weighting, and selecting the base classifiers of a voting ensemble. We compare NICD with several other noise handling techniques that do not consider classifier diversity on a set of 54 data sets and 5 learning algorithms. NICD significantly increases the classification accuracy over the other considered approaches and is effective across a broad set of data sets and learning algorithms.

Download

Tony Martinez

Uploads

Papers by Tony Martinez

Log In