Justin Bui | Baylor University (original) (raw)

Papers by Justin Bui

Research paper thumbnail of nanoK12 - A Tiny Portal with Even Smaller Ideas

Research paper thumbnail of Cascade watchdog: a multi-tiered adversarial guard for outlier detection

Signal, Image and Video Processing

The identification of out-of-distribution content is critical to the successful implementation of... more The identification of out-of-distribution content is critical to the successful implementation of neural networks. Watchdog techniques have been developed to support the detection of these inputs, but the performance can be limited by the amount of available data. Generative adversarial networks have displayed numerous capabilities, including the ability to generate facsimiles with excellent accuracy. This paper presents and empirically evaluates a multi-tiered watchdog, which is developed using GAN generated data, for improved out-of-distribution detection. The cascade watchdog uses adversarial training to increase the amount of available data similar to the out-of-distribution elements that are more difficult to detect. Then, a specialized second guard is added sequentially. The results show a solid and significant improvement on the detection of the most challenging out-of-distribution inputs.

Research paper thumbnail of Symbiotic Hybrid Neural Network Watchdog For Outlier Detection

Neural networks are largely black boxes. A neural network trained to classify fruit may classify ... more Neural networks are largely black boxes. A neural network trained to classify fruit may classify a picture of a giraffe as a banana. A neural network watchdog's job is to identify such inputs, allowing a classifier to disregard such data. We investigate whether the watchdog should be separate from the neural network or symbiotically attached. We present empirical evidence that the symbiotic watchdog performs better than when the neural networks are disjoint.

Research paper thumbnail of Classification of Common Waveforms Including a Watchdog for Unknown Signals

ArXiv, 2021

In this paper, we examine the use of a deep multilayer perceptron model architecture to classify ... more In this paper, we examine the use of a deep multilayer perceptron model architecture to classify received signal samples as coming from one of four common waveforms, Single Carrier (SC), Single-Carrier Frequency Division Multiple Access (SC-FDMA), Orthogonal Frequency Division Multiplexing (OFDM), and Linear Frequency Modulation (LFM), used in communication and radar networks. Synchronization of the signals is not needed as we assume there is an unknown and uncompensated time and frequency offset. An autoencoder with a deep CNN architecture is also examined to create a new fifth classification category of an unknown waveform type. This is accomplished by calculating a minimum and maximum threshold values from the root mean square error (RMSE) of the radar and communication waveforms. The classifier and autoencoder work together to monitor a spectrum area to identify the common waveforms inside the area of operation along with detecting unknown waveforms. Results from testing showed ...

Research paper thumbnail of Symbiotic Hybrid Neural Network Watchdog For Outlier Detection

Neural networks are largely black boxes. A neural network trained to classify fruit may classify ... more Neural networks are largely black boxes. A neural network trained to classify fruit may classify a picture of a giraffe as a banana. A neural network watchdog's job is to identify such inputs, allowing a classifier to disregard such data. We investigate whether the watchdog should be separate from the neural network or symbiotically attached. We present empirical evidence that the symbiotic watchdog performs better than when the neural networks are disjoint.

Research paper thumbnail of Autoencoder Watchdog Outlier Detection for Classifiers

Proceedings of the 13th International Conference on Agents and Artificial Intelligence, 2021

Neural networks have often been described as black boxes. A generic neural network trained to dif... more Neural networks have often been described as black boxes. A generic neural network trained to differentiate between kittens and puppies will classify a picture of a kumquat as a kitten or a puppy. An autoencoder watchdog screens trained classifier/regression machine input candidates before processing, e.g. to first test whether the neural network input is a puppy or a kitten. Preliminary results are presented using convolutional neural networks and convolutional autoencoder watchdogs using MNIST images.

Research paper thumbnail of Generatively Augmented Neural Network Watchdog for Image Classification Networks

ArXiv, 2021

The identification of out-of-distribution data is vital to the deployment of classification netwo... more The identification of out-of-distribution data is vital to the deployment of classification networks. For example, a generic neural network that has been trained to differentiate between images of dogs and cats can only classify an input as either a dog or a cat. If a picture of a car or a kumquat were to be supplied to this classifier, the result would still be either a dog or a cat. In order to mitigate this, techniques such as the neural network watchdog have been developed. The compression of the image input into the latent layer of the autoencoder defines the region of in-distribution in the image space. This in-distribution set of input data has a corresponding boundary in the image space. The watchdog assesses whether inputs are in inside or outside this boundary. This paper demonstrates how to sharpen this boundary using generative network training data augmentation thereby bettering the discrimination and overall performance of the watchdog.

Research paper thumbnail of nanoK12 - A Tiny Portal with Even Smaller Ideas

Research paper thumbnail of Cascade watchdog: a multi-tiered adversarial guard for outlier detection

Signal, Image and Video Processing

The identification of out-of-distribution content is critical to the successful implementation of... more The identification of out-of-distribution content is critical to the successful implementation of neural networks. Watchdog techniques have been developed to support the detection of these inputs, but the performance can be limited by the amount of available data. Generative adversarial networks have displayed numerous capabilities, including the ability to generate facsimiles with excellent accuracy. This paper presents and empirically evaluates a multi-tiered watchdog, which is developed using GAN generated data, for improved out-of-distribution detection. The cascade watchdog uses adversarial training to increase the amount of available data similar to the out-of-distribution elements that are more difficult to detect. Then, a specialized second guard is added sequentially. The results show a solid and significant improvement on the detection of the most challenging out-of-distribution inputs.

Research paper thumbnail of Symbiotic Hybrid Neural Network Watchdog For Outlier Detection

Neural networks are largely black boxes. A neural network trained to classify fruit may classify ... more Neural networks are largely black boxes. A neural network trained to classify fruit may classify a picture of a giraffe as a banana. A neural network watchdog's job is to identify such inputs, allowing a classifier to disregard such data. We investigate whether the watchdog should be separate from the neural network or symbiotically attached. We present empirical evidence that the symbiotic watchdog performs better than when the neural networks are disjoint.

Research paper thumbnail of Classification of Common Waveforms Including a Watchdog for Unknown Signals

ArXiv, 2021

In this paper, we examine the use of a deep multilayer perceptron model architecture to classify ... more In this paper, we examine the use of a deep multilayer perceptron model architecture to classify received signal samples as coming from one of four common waveforms, Single Carrier (SC), Single-Carrier Frequency Division Multiple Access (SC-FDMA), Orthogonal Frequency Division Multiplexing (OFDM), and Linear Frequency Modulation (LFM), used in communication and radar networks. Synchronization of the signals is not needed as we assume there is an unknown and uncompensated time and frequency offset. An autoencoder with a deep CNN architecture is also examined to create a new fifth classification category of an unknown waveform type. This is accomplished by calculating a minimum and maximum threshold values from the root mean square error (RMSE) of the radar and communication waveforms. The classifier and autoencoder work together to monitor a spectrum area to identify the common waveforms inside the area of operation along with detecting unknown waveforms. Results from testing showed ...

Research paper thumbnail of Symbiotic Hybrid Neural Network Watchdog For Outlier Detection

Neural networks are largely black boxes. A neural network trained to classify fruit may classify ... more Neural networks are largely black boxes. A neural network trained to classify fruit may classify a picture of a giraffe as a banana. A neural network watchdog's job is to identify such inputs, allowing a classifier to disregard such data. We investigate whether the watchdog should be separate from the neural network or symbiotically attached. We present empirical evidence that the symbiotic watchdog performs better than when the neural networks are disjoint.

Research paper thumbnail of Autoencoder Watchdog Outlier Detection for Classifiers

Proceedings of the 13th International Conference on Agents and Artificial Intelligence, 2021

Neural networks have often been described as black boxes. A generic neural network trained to dif... more Neural networks have often been described as black boxes. A generic neural network trained to differentiate between kittens and puppies will classify a picture of a kumquat as a kitten or a puppy. An autoencoder watchdog screens trained classifier/regression machine input candidates before processing, e.g. to first test whether the neural network input is a puppy or a kitten. Preliminary results are presented using convolutional neural networks and convolutional autoencoder watchdogs using MNIST images.

Research paper thumbnail of Generatively Augmented Neural Network Watchdog for Image Classification Networks

ArXiv, 2021

The identification of out-of-distribution data is vital to the deployment of classification netwo... more The identification of out-of-distribution data is vital to the deployment of classification networks. For example, a generic neural network that has been trained to differentiate between images of dogs and cats can only classify an input as either a dog or a cat. If a picture of a car or a kumquat were to be supplied to this classifier, the result would still be either a dog or a cat. In order to mitigate this, techniques such as the neural network watchdog have been developed. The compression of the image input into the latent layer of the autoencoder defines the region of in-distribution in the image space. This in-distribution set of input data has a corresponding boundary in the image space. The watchdog assesses whether inputs are in inside or outside this boundary. This paper demonstrates how to sharpen this boundary using generative network training data augmentation thereby bettering the discrimination and overall performance of the watchdog.