Author name cluster

John Platt

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

18 papers

1 author row

NeurIPS Conference 2012 Conference Paper

Learning from the Wisdom of Crowds by Minimax Entropy

Dengyong Zhou
Sumit Basu
Yi Mao
John Platt

An important way to make large training sets is to gather noisy labels from crowds of nonexperts. We propose a minimax entropy principle to improve the quality of these labels. Our method assumes that labels are generated by a probability distribution over workers, items, and labels. By maximizing the entropy of this distribution, the method naturally infers item confusability and worker expertise. We infer the ground truth by minimizing the entropy of this distribution, which we show minimizes the Kullback-Leibler (KL) divergence between the probability distribution and the unknown truth. We show that a simple coordinate descent scheme can optimize minimax entropy. Empirically, our results are substantially better than previously published methods for the same problem.

NeurIPS Conference 2007 Conference Paper

Fast Variational Inference for Large-scale Internet Diagnosis

Emre Kiciman
David Maltz
John Platt

Web servers on the Internet need to maintain high reliability, but the cause of intermittent failures of web transactions is non-obvious. We use Bayesian inference to diagnose problems with web services. This diagnosis problem is far larger than any previously attempted: it requires inference of 10^4 possible faults from 10^5 observations. Further, such inference must be performed in less than a second. Inference can be done at this speed by combining a variational approximation, a mean-field approximation, and the use of stochastic gradient descent to optimize a variational cost function. We use this fast inference to diagnose a time series of anomalous HTTP requests taken from a real web service. The inference is fast enough to analyze network logs with billions of entries in a matter of hours.

NeurIPS Conference 2005 Conference Paper

Multiple Instance Boosting for Object Detection

Cha Zhang
John Platt
Paul Viola

A good image object detection algorithm is accurate, fast, and does not require exact locations of objects in a training set. We can create such an object detector by taking the architecture of the Viola-Jones detector cascade and training it with a new variant of boosting that we call MILBoost. MILBoost uses cost functions from the Multiple Instance Learning literature combined with the AnyBoost framework. We adapt the feature selection criterion of MILBoost to optimize the performance of the Viola-Jones cascade. Experiments show that the detection rate is up to 1. 6 times better using MILBoost. This increased detection rate shows the advantage of simultaneously learning the locations and scales of the objects in the training set along with the parameters of the classifier.

NeurIPS Conference 2003 Conference Paper

Fast Embedding of Sparse Similarity Graphs

John Platt

This paper applies fast sparse multidimensional scaling (MDS) to a large graph of music similarity, with 267K vertices that represent artists, al- bums, and tracks; and 3. 22M edges that represent similarity between those entities. Once vertices are assigned locations in a Euclidean space, the locations can be used to browse music and to generate playlists. MDS on very large sparse graphs can be effectively performed by a family of algorithms called Rectangular Dijsktra (RD) MDS algorithms. These RD algorithms operate on a dense rectangular slice of the distance matrix, created by calling Dijsktra a constant number of times. Two RD algorithms are compared: Landmark MDS, which uses the Nystr(cid: 246)m ap- proximation to perform MDS; and a new algorithm called Fast Sparse Embedding, which uses FastMap. These algorithms compare favorably to Laplacian Eigenmaps, both in terms of speed and embedding quality.

NeurIPS Conference 2001 Conference Paper

Learning a Gaussian Process Prior for Automatically Generating Music Playlists

John Platt
Christopher Burges
Steven Swenson
Christopher Weare
Alice Zheng

This paper presents AutoDJ: a system for automatically generating mu- sic playlists based on one or more seed songs selected by a user. AutoDJ uses Gaussian Process Regression to learn a user preference function over songs. This function takes music metadata as inputs. This paper further introduces Kernel Meta-Training, which is a method of learning a Gaussian Process kernel from a distribution of functions that generates the learned function. For playlist generation, AutoDJ learns a kernel from a large set of albums. This learned kernel is shown to be more effective at predicting users’ playlists than a reasonable hand-designed kernel.

NeurIPS Conference 2000 Conference Paper

Speech Denoising and Dereverberation Using Probabilistic Models

Hagai Attias
John Platt
Alex Acero
Li Deng

This paper presents a unified probabilistic framework for denoising and dereverberation of speech signals. The framework transforms the denois(cid: 173) ing and dereverberation problems into Bayes-optimal signal estimation. The key idea is to use a strong speech model that is pre-trained on a large data set of clean speech. Computational efficiency is achieved by using variational EM, working in the frequency domain, and employing conjugate priors. The framework covers both single and multiple micro(cid: 173) phones. We apply this approach to noisy reverberant speech signals and get results substantially better than standard methods.

NeurIPS Conference 1999 Conference Paper

Large Margin DAGs for Multiclass Classification

John Platt
Nello Cristianini
John Shawe-Taylor

We present a new learning architecture: the Decision Directed Acyclic Graph (DDAG), which is used to combine many two-class classifiers into a multiclass classifier. For an N -class problem, the DDAG con(cid: 173) tains N(N - 1)/2 classifiers, one for each pair of classes. We present a VC analysis of the case when the node classifiers are hyperplanes; the re(cid: 173) sulting bound on the test error depends on N and on the margin achieved at the nodes, but not on the dimension of the space. This motivates an algorithm, DAGSVM, which operates in a kernel-induced feature space and uses two-class maximal margin hyperplanes at each decision-node of the DDAG. The DAGSVM is substantially faster to train and evalu(cid: 173) ate than either the standard algorithm or Max Wins, while maintaining comparable accuracy to both of these algorithms.

NeurIPS Conference 1999 Conference Paper

Support Vector Method for Novelty Detection

Bernhard Schölkopf
Robert Williamson
Alex Smola
John Shawe-Taylor
John Platt

Suppose you are given some dataset drawn from an underlying probabil(cid: 173) ity distribution P and you want to estimate a "simple" subset S of input space such that the probability that a test point drawn from P lies outside of S equals some a priori specified l/ between 0 and 1. We propose a method to approach this problem by trying to estimate a function f which is positive on S and negative on the complement. The functional form of f is given by a kernel expansion in terms of a poten(cid: 173) tially small subset of the training data; it is regularized by controlling the length of the weight vector in an associated feature space. We provide a theoretical analysis of the statistical performance of our algorithm. The algorithm is a natural extension of the support vector algorithm to the case of unlabelled data.

NeurIPS Conference 1998 Conference Paper

Using Analytic QP and Sparseness to Speed Training of Support Vector Machines

John Platt

Training a Support Vector Machine (SVM) requires the solution of a very large quadratic programming (QP) problem. This paper proposes an al(cid: 173) gorithm for training SVMs: Sequential Minimal Optimization, or SMO. SMO breaks the large QP problem into a series of smallest possible QP problems which are analytically solvable. Thus, SMO does not require a numerical QP library. SMO's computation time is dominated by eval(cid: 173) uation of the kernel, hence kernel optimizations substantially quicken SMO. For the MNIST database, SMO is 1. 7 times as fast as PCG chunk(cid: 173) ing; while for the UCI Adult database and linear SVMs, SMO can be 1500 times faster than the PCG chunking algorithm.

NeurIPS Conference 1996 Conference Paper

A Constructive RBF Network for Writer Adaptation

John Platt
Nada Matic

This paper discusses a fairly general adaptation algorithm which augments a standard neural network to increase its recognition ac(cid: 173) curacy for a specific user. The basis for the algorithm is that the output of a neural network is characteristic of the input, even when the output is incorrect. We exploit this characteristic output by using an Output Adaptation Module (OAM) which maps this out(cid: 173) put into the correct user-dependent confidence vector. The OAM is a simplified Resource Allocating Network which constructs ra(cid: 173) dial basis functions on-line. We applied the OAM to construct a writer-adaptive character recognition system for on-line hand(cid: 173) printed characters. The OAM decreases the word error rate on a test set by an average of 45%, while creating only 3 to 25 basis functions for each writer in the test set.

NeurIPS Conference 1995 Conference Paper

A Neural Network Classifier for the I100 OCR Chip

John Platt
Timothy Allen

This paper describes a neural network classifier for the 11000 chip, which optically reads the E13B font characters at the bottom of checks. The first layer of the neural network is a hardware linear classifier which recognizes the characters in this font. A second software neural layer is implemented on an inexpensive microprocessor to clean up the re(cid: 173) sults of the first layer. The hardware linear classifier is mathematically specified using constraints and an optimization principle. The weights of the classifier are found using the active set method, similar to Vap(cid: 173) nik's separating hyperplane algorithm. In 7. 5 minutes ofSPARC 2 time, the method solves for 1523 Lagrange mUltipliers, which is equivalent to training on a data set of approximately 128, 000 examples. The result(cid: 173) ing network performs quite well: when tested on a test set of 1500 real checks, it has a 99. 995% character accuracy rate. 1 A BRIEF OVERVIEW OF THE 11000 CHIP At Synaptics, we have created the 11000, an analog VLSI chip that, when combined with associated software, optically reads the E13B font from the bottom of checks. This E13B font is shown in figure 1. The overall architecture of the 11000 chip is shown in figure 2. The 11000 recognizes checks hand-swiped through a slot. A lens focuses the image of the bottom of the check onto the retina. The retina has circuitry which locates the vertical position of the characters on the check. The retina then sends an image vertically centered around a possible character to the classifier. The classifier in the nooo has a tough job. It must be very accurate and immune to noise and ink scribbles in the input. Therefore, we decided to use an integrated segmentation and recognition approach (Martin & Pittman, 1992)(Platt, et al. , 1992). When the classifier produces a strong response, we know that a character is horizontally centered in the retina. A Neural Network Classifier for the 11000 OCR Chip 939 Figure 1: The E13B font, as seen by the 11000 chip

NeurIPS Conference 1994 Conference Paper

A Convolutional Neural Network Hand Tracker

Steven Nowlan
John Platt

We describe a system that can track a hand in a sequence of video frames and recognize hand gestures in a user-independent manner. The system locates the hand in each video frame and determines if the hand is open or closed. The tracking system is able to track the hand to within ±10 pixels of its correct location in 99. 7% of the frames from a test set containing video sequences from 18 dif(cid: 173) ferent individuals captured in 18 different room environments. The gesture recognition network correctly determines if the hand being tracked is open or closed in 99. 1 % of the frames in this test set. The system has been designed to operate in real time with existing hardware.

NeurIPS Conference 1993 Conference Paper

Postal Address Block Location Using a Convolutional Locator Network

Ralph Wolf
John Platt

This paper describes the use of a convolutional neural network to perform address block location on machine-printed mail pieces. Locating the address block is a difficult object recognition problem because there is often a large amount of extraneous printing on a mail piece and because address blocks vary dramatically in size and shape. We used a convolutional locator network with four outputs, each trained to find a different corner of the address block. A simple set of rules was used to generate ABL candidates from the network output. The system performs very well: when allowed five guesses, the network will tightly bound the address delivery information in 98. 2% of the cases.

NeurIPS Conference 1992 Conference Paper

An Analog VLSI Chip for Radial Basis Functions

Janeen Anderson
John Platt
David Kirk

We have designed, fabricated, and tested an analog VLSI chip which computes radial basis functions in parallel. We have de(cid: 173) veloped a synapse circuit that approximates a quadratic function. We aggregate these circuits to form radial basis functions. These radial basis functions are then averaged together using a follower aggregator.

NeurIPS Conference 1991 Conference Paper

Networks for the Separation of Sources that are Superimposed and Delayed

John Platt
Federico Faggin

We have created new networks to unmix signals which have been mixed either with time delays or via filtering. We first show that a subset of the Herault-Jutten learning rules fulfills a principle of minimum output power. We then apply this principle to extensions of the Herault-Jutten network which have delays in the feedback path. Our networks perform well on real speech and music signals that have been mixed using time delays or filtering.

NeurIPS Conference 1990 Conference Paper

Leaning by Combining Memorization and Gradient Descent

John Platt

We have created a radial basis function network that allocates a new computational unit whenever an unusual pattern is presented to the network. The network learns by allocating new units and adjusting the parameters of existing units. If the network performs poorly on a presented pattern, then a new unit is allocated which memorizes the response to the presented pattern. If the network performs well on a presented pattern, then the network parameters are updated using standard LMS gradient descent. For predicting the Mackey Glass chaotic time series, our network learns much faster than do those using back-propagation and uses a comparable number of synapses.

NeurIPS Conference 1989 Conference Paper

Analog Circuits for Constrained Optimization

John Platt

This paper explores whether analog circuitry can adequately per(cid: 173) form constrained optimization. Constrained optimization circuits are designed using the differential multiplier method. These cir(cid: 173) cuits fulfill time-varying constraints correctly. Example circuits in(cid: 173) clude a quadratic programming circuit and a constrained flip-flop.

NeurIPS Conference 1987 Conference Paper

Constrained Differential Optimization

John Platt
Alan Barr

Many optimization models of neural networks need constraints to restrict the space of outputs to a subspace which satisfies external criteria. Optimizations using energy methods yield "forces" which act upon the state of the neural network. The penalty method, in which quadratic energy constraints are added to an existing optimization energy, has become popular recently, but is not guaranteed to satisfy the constraint conditions when there are other forces on the neural model or when there are multiple constraints. In this paper, we present the basic differential multiplier method (BDMM), which satisfies constraints exactly; we create forces which gradually apply the constraints over time, using "neurons" that estimate Lagrange multipliers. The basic differential multiplier method is a differential version of the method of multipliers from Numerical Analysis. We prove that the differential equations locally converge to a constrained minimum. Examples of applications of the differential method of multipliers include enforcing permutation codewords in the analog decoding problem and enforcing valid tours in the traveling salesman problem.