Computer Engineering Commons^™

Sequential Frame-Interpolation And Dct-Based Video Compression Framework, Yeganeh Jalalpour, Wu-Chi Feng, Feng Liu

Computer Science Faculty Publications and Presentations

Video data is ubiquitous; capturing, transferring, and storing even compressed video data is challenging because it requires substantial resources. With the large amount of video traffic being transmitted on the internet, any improvement in compressing such data, even small, can drastically impact resource consumption. In this paper, we present a hybrid video compression framework that unites the advantages of both DCT-based and interpolation-based video compression methods in a single framework. We show that our work can deliver the same visual quality or, in some cases, improve visual quality while reducing the bandwidth by 10--20%.

On The (Im)Practicality Of Adversarial Perturbation For Image Privacy, Arezoo Rajabi, Rakesh B. Bobba, Mike Rosulek, Charles Wright, Wu-Chi Feng

Computer Science Faculty Publications and Presentations

Image hosting platforms are a popular way to store and share images with family members and friends. However, such platforms typically have full access to images raising privacy concerns. These concerns are further exacerbated with the advent of Convolutional Neural Networks (CNNs) that can be trained on available images to automatically detect and recognize faces with high accuracy.

Recently, adversarial perturbations have been proposed as a potential defense against automated recognition and classification of images by CNNs. In this paper, we explore the practicality of adversarial perturbation based approaches as a privacy defense against automated face recognition. Specifically, we first …

Extending The Functional Subnetwork Approach To A Generalized Linear Integrate-And-Fire Neuron Model, Nicholas Szczecinski, Roger Quinn, Alexander J. Hunt

Mechanical and Materials Engineering Faculty Publications and Presentations

Engineering neural networks to perform specific tasks often represents a monumental challenge in determining network architecture and parameter values. In this work, we extend our previously-developed method for tuning networks of non-spiking neurons, the “Functional subnetwork approach” (FSA), to the tuning of networks composed of spiking neurons. This extension enables the direct assembly and tuning of networks of spiking neurons and synapses based on the network’s intended function, without the use of global optimization ormachine learning. To extend the FSA, we show that the dynamics of a generalized linear integrate and fire (GLIF) neuronmodel have fundamental similarities to those of …

Flight Simulator Modeling Using Recurrent Neural Networks, Nickolas Sabatini, Andreas Natsis

Undergraduate Research & Mentoring Program

Recurrent neural networks (RNNs) are a form of machine learning used to predict future values. This project uses RNNs tor predict future values for a flight simulator. Coded in Python using the Keras library, the model demonstrates training loss and validation loss, referring to the error when training the model.

Design Of A Canine Inspired Quadruped Robot As A Platform For Synthetic Neural Network Control, Cody Warren Scharzenberger

Dissertations and Theses

Legged locomotion is a feat ubiquitous throughout the animal kingdom, but modern robots still fall far short of similar achievements. This paper presents the design of a canine-inspired quadruped robot named DoggyDeux as a platform for synthetic neural network (SNN) research that may be one avenue for robots to attain animal-like agility and adaptability. DoggyDeux features a fully 3D printed frame, 24 braided pneumatic actuators (BPAs) that drive four 3-DOF limbs in antagonistic extensor-flexor pairs, and an electrical system that allows it to respond to commands from a SNN comprised of central pattern generators (CPGs). Compared to the previous version …

The Applications Of Grid Cells In Computer Vision, Keaton Kraiger

Undergraduate Research & Mentoring Program

In this study we present a novel method for position and scale invariant object representation based on a biologically-inspired framework. Grid cells are neurons in the entorhinal cortex whose multiple firing locations form a periodic triangular array, tiling the surface of an animal’s environment. We propose a model for simple object representation that maintains position and scale invariance, in which grid maps capture the fundamental structure and features of an object. The model provides a mechanism for identifying feature locations in a Cartesian plane and vectors between object features encoded by grid cells. It is shown that key object features …

Exploring And Expanding The One-Pixel Attack, Umairullah Khan, Walt Woods

Undergraduate Research & Mentoring Program

In machine learning research, adversarial examples are normal inputs to a classifier that have been specifically perturbed to cause the model to misclassify the input. These perturbations rarely affect the human readability of an input, even though the model’s output is drastically different. Recent work has demonstrated that image-classifying deep neural networks (DNNs) can be reliably fooled with the modification of a single pixel in the input image, without knowledge of a DNN’s internal parameters. This “one-pixel attack” utilizes an iterative evolutionary optimizer known as differential evolution (DE) to find the most effective pixel to perturb, via the evaluation of …

Combining Algorithms For More General Ai, Mark Robert Musil

Undergraduate Research & Mentoring Program

Two decades since the first convolutional neural network was introduced the AI sub-domains of classification, regression and prediction still rely heavily on a few ML architectures despite their flaws of being hungry for data, time, and high-end hardware while still lacking generality. In order to achieve more general intelligence that can perform one-shot learning, create internal representations, and recognize subtle patterns it is necessary to look for new ML system frameworks. Research on the interface between neuroscience and computational statistics/machine learning has suggested that combined algorithms may increase AI robustness in the same way that separate brain regions specialize. In …

Radiation Source Localization By Using Backpropagation Neural Network, Jian Meng, Christof Teuscher, Walt Woods

Student Research Symposium

The most difficult part of the radiation localization is that we cannot use the traditional acoustic localization method to determine where the radiation source is. It’s mainly because the electromagnetic waves are totally different with the sound wave. From the expression of the radioactive intensity, we can tell that the intensity of radiation not only depend on the distance from the radiation but also related to the type of the nuclide. In general, the relationship between the intensity and the distance satisfy the inverse-square law, which is a non-linear relationship. In other words, if we can use the measurement and …

Video Frame Interpolation Via Adaptive Separable Convolution, Simon Niklaus, Long Mai, Feng Liu

Computer Science Faculty Publications and Presentations

Standard video frame interpolation methods first estimate optical flow between input frames and then synthesize an intermediate frame guided by motion. Recent approaches merge these two steps into a single convolution process by convolving input frames with spatially adaptive kernels that account for motion and re-sampling simultaneously. These methods require large kernels to handle large motion, which limits the number of pixels whose kernels can be estimated at once due to the large memory demand. To address this problem, this paper formulates frame interpolation as local separable convolution over input frames using pairs of 1D kernels. Compared to regular 2D …

Information Representation And Computation Of Spike Trains In Reservoir Computing Systems With Spiking Neurons And Analog Neurons, Amin Almassian

Dissertations and Theses

Real-time processing of space-and-time-variant signals is imperative for perception and real-world problem-solving. In the brain, spatio-temporal stimuli are converted into spike trains by sensory neurons and projected to the neurons in subcortical and cortical layers for further processing.

Reservoir Computing (RC) is a neural computation paradigm that is inspired by cortical Neural Networks (NN). It is promising for real-time, on-line computation of spatio-temporal signals. An RC system incorporates a Recurrent Neural Network (RNN) called reservoir, the state of which is changed by a trajectory of perturbations caused by a spatio-temporal input sequence. A trained, non- recurrent, linear readout-layer interprets the …

Computational Capacity And Energy Consumption Of Complex Resistive Switch Networks, Jens Bürger, Alireza Goudarzi, Darko Stefanovic, Christof Teuscher

Electrical and Computer Engineering Faculty Publications and Presentations

Resistive switches are a class of emerging nanoelectronics devices that exhibit a wide variety of switching characteristics closely resembling behaviors of biological synapses. Assembled into random networks, such resistive switches produce emerging behaviors far more complex than that of individual devices. This was previously demonstrated in simulations that exploit information processing within these random networks to solve tasks that require nonlinear computation as well as memory. Physical assemblies of such networks manifest complex spatial structures and basic processing capabilities often related to biologically-inspired computing. We model and simulate random resistive switch networks and analyze their computational capacities. We provide a …