• Publications
  • Influence
A training algorithm for optimal margin classifiers
A training algorithm that maximizes the margin between the training patterns and the decision boundary is presented. Expand
Backpropagation Applied to Handwritten Zip Code Recognition
The ability of learning networks to generalize can be greatly enhanced by providing constraints from the task domain. Expand
Handwritten Digit Recognition with a Back-Propagation Network
We present an application of back-propagation networks to handwritten digit recognition with 1% error rate and about 9% reject rate. Expand
A 12 b 75 MS/s pipelined ADC using open-loop residue amplification
The multi-bit first stage of a 12 b 75 MS/s pipelined ADC uses an open-loop gain stage to achieve more than 60% residue amplifier power savings over a conventional implementation. Expand
The design of sigma-delta modulation analog-to-digital converters
The author examines the practical design criteria for implementing oversampled analog/digital converters based on second-order sigma-delta ( Sigma Delta ) modulation. Expand
A three-axis micromachined accelerometer with a CMOS position-sense interface and digital offset-trim electronics
This paper describes a three-axis accelerometer implemented in a surface-micromachining technology with integrated CMOS that measures changes in a capacitive half-bridge to detect deflections of a proof mass, which result from acceleration input. Expand
Handwritten digit recognition: applications of neural network chips and automatic learning
Two novel methods for achieving handwritten digit recognition are described. Expand
Charge control of parallel-plate, electrostatic actuators and the tip-in instability
Controlling the charge, rather than the voltage, on a parallel-plate, electrostatic actuator theoretically permits stable operation for all deflections. Practically, we show that, using chargeExpand
An ultralow-energy ADC for Smart Dust
A low-energy successive approximation analog-to-digital converter targeted for use in distributed sensor networks is presented. Expand
17.6 A Fourth-Order Σ∆ Interface for Micromachined Inertial Sensors
This paper presents the design and implementation of a high-order interface for micromachined inertial sensors, which employs an electronic filter in series with the mechanical sensor element in a inertial sensor improves the resolution by highly attenuating the quantization noise in the signal band. Expand