ARGUS is a multi-agent visitor identi cation system distributed over several workstations. Human faces are extracted from security camera images by a neuralnetwork-based face detector, and identi ed as frequent visitors by ARENA, a memory-based face recognition system. ARGUS then uses a messaging system to notify hosts that their guests have arrived. An interface agent enables users to submit f...

We propose a new cognitive framework for option price modelling, using quantum neural computation formalism. Briefly, when we apply a classical nonlinear neuralnetwork learning to a linear quantum Schrödinger equation, as a result we get a nonlinear Schrödinger equation (NLS), performing as a quantum stochastic filter. In this paper, we present a bidirectional quantum associative memory model f...

ARGUS is a multi-agent visitor identification system distributed over several workstations. Human faces are extracted from security camera images by a neuralnetwork-based face detector, and identified as frequent visitors by ARENA, a memory-based face recognition system. ARGUS then uses a messaging system to notify hosts that their guests have arrived. An interface agent enables users to submit...

We propose deeply-supervised nets (DSN), a method that simultaneously minimizes classification error and improves the directness and transparency of the hidden layer learning process. We focus our attention on three aspects of traditional convolutional-neuralnetwork-type (CNN-type) architectures: (1) transparency in the effect intermediate layers have on overall classification; (2) discriminati...

This paper addresses the problem of deadbeat control in fully controlled high-power-factor rectifiers. Improved deadbeat control can be achieved through the use of neuralnetwork-based predictors for the input-current reference to the rectifier. In this application, on-line training is absolutely required. In order to achieve sufficiently fast on-line training, a new random-search algorithm is p...

This paper presents about the feedforward neural networks for various waveform processing and delayless filtering that are applicable to power electronics. Neuralnetwork-based processing of waves gives considerable simplification of hardware and/or software that are traditionally used for such applications. The voltage or current waveforms which have constant frequency but variable magnitudes c...

Accurate identification of unknown contacts crucial in military intelligence. Automated systems that quickly and accurately determine the identity of a contact could be a benefit in backing up electronic-signals identification methods. This work reports two experimental systems for ship classification from infrared FLIR images. In an edge-histogram approach, we used the histogram of the binned ...

In this paper, we use deep neural networks for inverting face sketches to synthesize photorealistic face images. We first construct a semi-simulated dataset containing a very large number of computergenerated face sketches with different styles and corresponding face images by expanding existing unconstrained face data sets. We then train models achieving state-of-the-art results on both comput...

A Neural Network trigger for bb events based on the SVT microvertex processor of experiment CDF at Fermilab is presented. It exploits correlations among track impact parameters and azimuths calculated by the SVT from the SVX microvertex detector data. The neural trigger is meant for implementation on the systolic Siemens microprocessor MA16, which has already been used in a neural-network trigg...

Prefrontal cortex (PFC) has been implicated in the ability to switch behavioral strategies in response to changes in reward contingencies. A recent experimental study has shown that separate subpopulations of neurons in the prefrontal cortex were activated when rats switched between allocentric place strategies and egocentric response strategies in the plus maze. In this paper we propose a simp...