Search

Deep neural networks (DNNs) are gaining popularity in a wide range of domains, ranging from speech and video recognition to healthcare. With this increased adoption comes the pressing need for securing DNN execution environments on CPUs, GPUs, and ASICs. While there are active research efforts in supporting a trusted execution environment (TEE) on CPUs, the exploration in supporting TEEs on accelerators is limited, with only a few solutions available [18, 19, 27]. A key limitation along this line of work is that these secure DNN accelerators narrowly consider a few specific architectures. The design choices and the associated cost for securing these architectures do not transfer to other diverse architectures. This paper strives to address this limitation by developing a design space exploration tool for supporting TEEs on diverse DNN accelerators. We target secure DNN accelerators equipped with cryptographic engines where the cryptographic operations are closely coupled with the data movement in the accelerators. These operations significantly complicate the scheduling for DNN accelerators, as the scheduling needs to account for the extra on-chip computation and off-chip memory accesses introduced by these cryptographic operations, and even needs to account for potential interactions across DNN layers. We tackle these challenges in our tool, called SecureLoop, by introducing a scheduling search engine with the following attributes: 1) considers the cryptographic overhead associated with every off-chip data access, 2) uses an efficient modular arithmetic technique to compute the optimal authentication block assignment for each individual layer, and 3) uses a simulated annealing algorithm to perform cross-layer optimizations. Compared to the conventional schedulers, our tool finds the schedule for secure DNN designs with up to 33.2% speedup and 50.2% improvement of energy-delay-product.

2022 International Electron Devices Meeting (IEDM), San Francisco, CA, USA, III-Nitrides are attractive as field emission devices for high frequency, high power, and harsh environment applications. A wet-based digital etching and a novel device geometry was used to demonstrate GaN vertical self-alignedgate (SAG) field emitter arrays (FEA) with uniform tips of sub- 10 nm tip radius. The best GaN FEA has a current density (JA) of 10 A/cm2 at VGE = 50 V, which is better than the state-of-the-art Si field emitter arrays at the same bias condition., Department of Defense (DoD)

Point-of-care testing using paper-based lateral flow assays (LFAs) has emerged as an attractive diagnostic platform. However, detecting small molecules such as cortisol using LFAs is challenging due to limited binding sites and weak signal generation. Here, we report the development of cortisol-specific aptamer-based probes and a paper-based origami preconcentrator (POP) to amplify the probe signal. The cortisol-specific aptamers were conjugated onto gold nanoparticles and hybridized with signal probes to create the cortisol-specific signal-on probe. POP, consisting of patterned layers with convergent wicking zones, induces electrokinetic preconcentration of the released signaling probes. By integrating cortisol-selective aptamer-based probes and POP, we accurately diagnosed cortisol levels within 30 min of signal probe incubation, followed by 10 min of preconcentration. Our sensor was able to detect cortisol levels in the range of 25–1000 ng/mL, with typical cortisol levels in plasma ranging from 40 to 250 ng/mL falling within this range. The successful detection of the wide range of cortisol samples using this approach highlights the potential of this platform as a point-of-care testing tool, particularly for lateral flow assay-based detection of small molecules like cortisol. Our approach offers a convenient and reliable method of cortisol level testing with a portable and accessible diagnosis device.

On-device learning and efficient fine-tuning enable continuous and privacy-preserving customization (e.g., locally fine-tuning large language models on personalized data). However, existing training frameworks are designed for cloud servers with powerful accelerators (e.g., GPUs, TPUs) and lack the optimizations for learning on the edge, which faces challenges of resource limitations and edge hardware diversity. We introduce PockEngine: a tiny, sparse and efficient engine to enable fine-tuning on various edge devices. PockEngine supports sparse backpropagation: it prunes the backward graph and sparsely updates the model with measured memory saving and latency reduction while maintaining the model quality. Secondly, PockEngine is compilation first: the entire training graph (including forward, backward and optimization steps) is derived at compile-time, which reduces the runtime overhead and brings opportunities for graph transformations. PockEngine also integrates a rich set of training graph optimizations, thus can further accelerate the training cost, including operator reordering and backend switching. PockEngine supports diverse applications, frontends and hardware backends: it flexibly compiles and tunes models defined in PyTorch/TensorFlow/Jax and deploys binaries to mobile CPU/GPU/DSPs. We evaluated PockEngine on both vision models and large language models. PockEngine achieves up to 15 × speedup over off-the-shelf TensorFlow (Raspberry Pi), 5.6 × memory saving back-propagation (Jetson AGX Orin). Remarkably, PockEngine enables fine-tuning LLaMav2-7B on NVIDIA Jetson AGX Orin at 550 tokens/s, 7.9 × faster than the PyTorch.

Holographic displays generate Three-Dimensional (3D) images by displaying single-color holograms time-sequentially, each lit by a single-color light source. However, representing each color one by one limits brightness in holographic displays. This paper introduces a new driving scheme for realizing brighter images in holographic displays. Unlike the conventional driving scheme, our method utilizes three light sources to illuminate each displayed hologram simultaneously at various intensity levels. In this way, our method reconstructs a multiplanar three-dimensional target scene using consecutive multi-color holograms and persistence of vision. We co-optimize multi-color holograms and required intensity levels from each light source using a gradient descent-based optimizer with a combination of application-specific loss terms. We experimentally demonstrate that our method can increase the intensity levels in holographic displays up to three times, reaching a broader range and unlocking new potentials for perceptual realism in holographic displays.

We report graphene films composed mostly of one or two layers of graphene grown by controlled carbon precipitation on the surface of polycrystalline Ni thin films during atmospheric chemical vapor deposition (CVD). Controlling both the methane concentration during CVD and the substrate cooling rate during graphene growth can significantly improve the thickness uniformity. As a result, one- or two- layer graphene regions occupy up to 87% of the film area. Single layer coverage accounts for 5%–11% of the overall film. These regions expand across multiple grain boundaries of the underlying polycrystalline Ni film. The number density of sites with multilayer graphene/graphite (>2 layers) is reduced as the cooling rate decreases. These films can also be transferred to other substrates and their sizes are only limited by the sizes of the Ni film and the CVD chamber. Here, we demonstrate the formation of films as large as 1 in2. These findings represent an important step towards the fabrication of large-scale high-quality graphene samples., National Science Foundation (U.S.) (CTS 05-06830), National Science Foundation (U.S.) (DMR07-04197)

2024 IEEE Custom Integrated Circuits Conference April 21st – 24th, 2024 Denver, CO U.S., Machine learning (ML) accelerators provide energy efficient neural network (NN) implementations for applications such as speech recognition and image processing. Recently, digital IMC has been proposed to reduce data transfer energy, while still allowing for higher bitwidths and accuracies necessary for many workloads, especially with technology scaling [1,2]. Privacy of ML workloads can be exploited with physical side-channel attacks (SCAs) or bus probing attacks (BPAs) [3] (Fig. 1). While SCAs correlate IC power consumption or EM emissions to data or operations, BPAs directly tap traces between the IC and off-chip memory. The inputs reflect private data collected on IoT devices, such as images of faces. The weights, typically stored off-chip, reveal information about proprietary private training datasets. This work presents the first IMC macro protected against SCAs and BPAs to mitigate these risks., National Science Foundation (NSF), MIT-IBM Watson AI Lab, MathWorks Engineering Fellowship

This booklet contains model lessons developed to familiarize students with the features of CD-ROM encyclopedias and to serve as a springboard for collaboration between media coordinators and classroom teachers. The lessons focus on integrating the skills needed to access information from electronic encyclopedias into social studies, language arts, and science using CD-ROM resources such as Comptons's Multimedia Encyclopedia, Grolier MultiMedia Encyclopedia, and Information Finder. The lessons include worksheets that provide a structure for observing, collecting, and reporting information. The first section of the publication contains Picture Search and Picture Explorer activities for grade 1-3 built around themes of animals and travel. The second section contains seven sets of activities for grades 4-8, with each set developed around a single theme, including whales, animals, explorers, discoveries, North Carolina, the world, and the United States. Each set in this section includes: (1) a topic page providing a lesson overview, a list of competency objectives, and suggestions for enriching the activities; (2) a teacher's page describing search path options and follow-up activities; and (3) student worksheets. (KRN)

ISSN: 2664-5661 The 6th APSCE International Conference on Computational Thinking and STEM Education 2022 (CTE-STEM 2022) is organized by the Asia-Pacific Society for Computers in Education (APSCE) and hosted by the Leiden-Delft-Erasmus Centre for Education and Learning (LDE-CEL). CTE-STEM 2022 is hosted for the first time in Europe by the Delft University of Technology (TU Delft), Delft, the Netherlands. This conference continues from the success of the previous four international Computational Thinking conferences organized by the National Institute of Education and Nanyang Technological University (NIE/NTU). This conference invites CT as well as STEM researchers and practitioners to share their findings, processes, and outcomes in the context of computing education or computational thinking.

Many real-world computations involve sparse data structures in the form of sparse matrices. A common strategy for optimizing sparse matrix operations is to reorder a matrix to improve data locality. However, it's not always clear whether reordering will provide benefits over the unordered matrix, as its effectiveness depends on several factors, such as structural features of the matrix, the reordering algorithm and the hardware that is used. This paper aims to establish the relationship between matrix reordering algorithms and the performance of sparse matrix operations. We thoroughly evaluate six different matrix reordering algorithms on 490 matrices across eight multicore architectures, focusing on the commonly used sparse matrix-vector multiplication (SpMV) kernel. We find that reordering based on graph partitioning provides better SpMV performance than the alternatives for a large majority of matrices, and that the resulting performance is explained through a combination of data locality and load balancing concerns., Scientific and Technological Research Council of Turkey (TÜBİTAK); European Union (EU); SparCity Project; European High-Performance Computing Joint Undertaking; Fundação para a Ciência e a Tecnologia (FCT); Research Council of Norway

Conversational agents (CAs) that deliver proactive interventions can benefit users by reducing their cognitive workload and improving performance. However, little is known regarding how such interventions would impact perception of CA’s appropriateness in voice-only, decision-making tasks. We conducted a within-subjects experiment (N=30) to evaluate the effect of CA’s feedback delivery strategy at three levels (no feedback, unsolicited, and solicited feedback) in an interactive food ordering scenario. We discovered that unsolicited feedback was perceived to be more appropriate than solicited feedback. Our results provide preliminary insights regarding the impact of proactive feedback on CA perception in decision-making tasks.

Energy differences in nuclei are paramount to understanding the nuclear systems far from stability, their rare decay modes, and trends in their relative stability. Modern ion trapping techniques such as Penning Trap Mass Spectrometry (PTMS), and Multiple Reflection Time Of Flight Mass Spectrometry (MRTOF-MS) have enabled the precision measurement of energy trends in even very short-lived nuclei, by allowing their masses to be measured. Such nuclei can be generated in large quantities at TRIUMF's Isotope Separator and Accelerator (ISAC), and TRIUMF's Ion Trap for Atomic and Nuclear science (TITAN) specializes in measuring the masses of the short-lived species produced at ISAC using an array of ion traps. This thesis describes measurements of the masses of neutron-deficient lanthanide elements produced at the ISAC facility at TRIUMF in Vancouver, Canada using the TITAN Multiple Reflection Time-Of-Flight (MR-TOF) mass spectrometer. The goal of these measurements was to extend the known existence of the N=82 shell closure up to Yb (Z=70), and to experimentally determine the location of the proton drip-line in Tm (Z=69). Mass measurements of 150Yb, 151Yb, and 153Yb confirm the continued existence of the N=82 shell closure. Additionally, new mass measurements of 149Tm and 150Tm were performed, as well as a re-measurement of 149Er that provides a correction to the literature value as published in the 2020 Atomic Mass Evaluation. Together, these mass data points provide the first experimental confirmation that 149Tm is the first proton-unbound species in the Tm isotopic chain. Furthermore, a new technique intended for rapidly cooling highly-charged ions (HCIs) produced via charge-breeding in TITAN's Electron Beam Ion Trap (EBIT) is experimentally tested. This technique involves sympathetically cooling the ions using free electrons, and holds the promise of cooling HCIs on a time-scale of seconds or less for studies with either short-lived or stable species. Technical challe

Recent successes of Deep Learning-powered AI are largely due to the trio of: algorithms, GPU computing, and big data. Data could take the shape of hospital records, satellite images, or the text in this paragraph. Deep Learning algorithms typically need massive collections of data before they can make reliable predictions. This limitation inspired investigation into a class of techniques referred to as Data Augmentation. Data Augmentation was originally developed as a set of label-preserving transformations used in order to simulate large datasets from small ones. For example, imagine developing a classifier that categorizes images as either a “cat” or a “dog”. After initial collection and labeling, there may only be 500 of these images, which are not enough data points to train a Deep Learning model. By transforming these images with Data Augmentations such as rotations and brightness modifications, more labeled images are available for model training and classification! In addition to applications for learning from limited labeled data, Data Augmentation can also be used for generalization testing. For example, we can augment the test set to set the visual style of images to “winter” and see how that impacts the performance of a stop sign detector. The dissertation begins with an overview of Deep Learning methods such as neural network architectures, gradient descent optimization, and generalization testing. Following an initial description of this technology, the dissertation explains overfitting. Overfitting is the crux of Deep Learning methods in which improvements to the training set do not lead to improvements on the testing set. To the rescue are Data Augmentation techniques, of which the Dissertation presents an overview of the augmentations used for both image and text data, as well as the promising potential of generative data augmentation with models such as ChatGPT. The dissertation then describes three major experimental works revolving around CIFAR-10, 2023, Includes bibliography., Degree granted: Dissertation (PhD)--Florida Atlantic University, 2023., Collection: FAU Electronic Theses and Dissertations Collection

Online advertising [100], as a multi-billion dollar business, provides a common marketing experience when people access online services using electronic devices, such as desktop computers, tablets, smartphones, and so on. Using the Internet as a means of advertising, different stakeholders take actions in the background to provide and deliver advertisements to users through numerous platforms, such as search engines, news sites, and social networks, where dedicated spots of areas are used to display advertisements (ads) along with search results, posts, or page content. Online advertising is mainly based on dynamically selecting ads through a real-time bidding (or auction) mechanism. Predicting user responses like clicking ads in e-commerce platforms and internet-based advertising systems, as the first measurable user response, is an essential step for many digital advertising and recommendation systems to capture the user’s propensity to follow up actions, such as purchasing a product or subscribing to a service. To maximize revenue and user satisfaction, online advertising platforms must predict the expected user behavior of each displayed advertisement and maximize the user’s expectations of clicking [28]. Based on this observed feedback, these systems are tailored to user preferences to decide the order in that ads or any promoted content should be served to them. This objective provides an incentive to develop new research by using ideas derived from different domains like machine learning and data mining combined with models for information retrieval and mathematical optimization. They introduce different machine learning and data mining methods that employ deep learning-based predictive models to learn the representation of input features with the aim of user response prediction. Feature representation learning is known as a fundamental task on how to input information is going to be represented in machine learning models. A good feature representation learni, 2023, Includes bibliography., Degree granted: Dissertation (PhD)--Florida Atlantic University, 2023., Collection: FAU Electronic Theses and Dissertations Collection

Skin cancer is a prevalent cancer that significantly contributes to global mortality rates. Early detection is crucial for a high survival rate. Dermatologists primarily rely on visual inspection to diagnose skin cancers, but this method is inaccurate. Deep learning algorithms can enhance the diagnostic accuracy of skin cancers. However, these algorithms require substantial labeled data for effective training. Acquiring annotated data for skin cancer classification is time-consuming, expensive, and necessitates expert annotation. Moreover, skin cancer datasets often suffer from imbalanced data distribution. Generative Adversarial Networks (GANs) can be used to overcome the challenges of data scarcity and lack of labels by automatically generating skin cancer images. However, training and testing data from different distributions can introduce domain shift and bias, impacting the model’s performance. This dissertation addresses this issue by developing deep learning-based domain adaptation models. Additionally, this research emphasizes deploying deep learning models on hardware to enable real-time skin cancer detection, facilitating accurate diagnoses by dermatologists. Deploying conventional deep learning algorithms on hardware is not preferred due to the problem of high resource consumption. Therefore, this dissertation presents spiking neural network-based (SNN) models designed specifically for hardware implementation. SNNs are preferred for their power-efficient behavior and suitability for hardware deployment., 2023, Includes bibliography., Degree granted: Dissertation (PhD)--Florida Atlantic University, 2023., Collection: FAU Electronic Theses and Dissertations Collection

Vision is a critical sense for many species, with the perception of motion being a fundamental aspect. This aspect often provides richer information than static images for understanding the environment. Motion recognition is a relatively simple computation compared to shape recognition. Many creatures can discriminate moving objects quite well while having virtually no capacity for recognizing stationary objects. Traditional methods for collision-free navigation require the reconstruction of a 3D model of the environment before planning an action. These methods face numerous limitations as they are computationally expensive and struggle to scale in unstructured and dynamic environments with a multitude of moving objects. This thesis proposes a more scalable and efficient alternative approach without 3D reconstruction. We focus on visual motion cues, specifically ’visual looming’, the relative expansion of objects on an image sensor. This concept allows for the perception of collision threats and facilitates collision-free navigation in any environment, structured or unstructured, regardless of the vehicle’s movement or the number of moving objects present., 2023, Includes bibliography., Degree granted: Dissertation (PhD)--Florida Atlantic University, 2023., Collection: FAU Electronic Theses and Dissertations Collection

In today’s world, data is generated at an unprecedented rate, and a significant portion of it is unstructured text data. The recent advancements in Natural Language Processing have enabled computers to understand and interpret human language. Data mining techniques were once unable to use text data due to the high dimensionality of text processing models. This limitation was overcome with the ability to represent data as text. This thesis aims to compare the predictive performance of structured versus unstructured text data in two different applications. The first application is in the field of real estate. We compare the performance of tabular real-estate data and unstructured text descriptions of homes to predict the house price. The second application is in translating Electronic Health Records (EHR) tabular data to text data for survival classification of COVID-19 patients. Lastly, we present a range of strategies and perspectives for future research., 2023, Includes bibliography., Degree granted: Thesis (MS)--Florida Atlantic University, 2023., Collection: FAU Electronic Theses and Dissertations Collection

The major objective of this dissertation was to create a framework which is used for medical image diagnosis. In this diagnosis, we brought classification and diagnosing of diseases through an Artificial Intelligence based framework, including COVID, Pneumonia, and Melanoma cancer through medical images. The algorithm ran on multiple datasets. A model was developed which detected the medical images through changing hyper-parameters. The aim of this work was to apply the new transfer learning framework DenseNet-201 for the diagnosis of the diseases and compare the results with the other deep learning models. The novelty in the proposed work was modifying the Dense Net 201 Algorithm, changing hyper parameters (source weights, Batch Size, Epochs, Architecture (number of neurons in hidden layer), learning rate and optimizer) to quantify the results. The novelty also included the training of the model by quantifying weights and in order to get more accuracy. During the data selection process, the data were cleaned, removing all the outliers. Data augmentation was used for the novel architecture to overcome overfitting and hence not producing false absurd results the computational performance was also observed. The proposed model results were also compared with the existing deep learning models and the algorithm was also tested on multiple datasets., 2023, Includes bibliography., Degree granted: Dissertation (PhD)--Florida Atlantic University, 2023., Collection: FAU Electronic Theses and Dissertations Collection

Mechanical search is a robotic problem where a robot needs to retrieve a target item that is partially or fully-occluded from its camera. State-of-the-art approaches for mechanical search either require an expensive search process to find the target item, or they require the item to be tagged with a radio frequency identification tag (e.g., RFID), making their approach beneficial only to tagged items in the environment. We present FuseBot, the first robotic system for RF-Visual mechanical search that enables efficient retrieval of both RF-tagged and untagged items in a pile. Rather than requiring all target items in a pile to be RF-tagged, FuseBot leverages the mere existence of an RF-tagged item in the pile to benefit both tagged and untagged items. Our design introduces two key innovations. The first is RF-Visual Mapping, a technique that identifies and locates RF-tagged items in a pile and uses this information to construct an RF-Visual occupancy distribution map. The second is RF-Visual Extraction, a policy formulated as an optimization problem that minimizes the number of actions required to extract the target object by accounting for the probabilistic occupancy distribution, the expected grasp quality, and the expected information gain from future actions. We built a real-time end-to-end prototype of our system on a UR5e robotic arm with in-hand vision and RF perception modules. We conducted over 200 real-world experimental trials to evaluate FuseBot and compare its performance to a state-of-the-art vision-based system named X-Ray (Danielczuk et al., in: 2020 IEEE/RSJ international conference on intelligent robots and systems (IROS), IEEE, 2020). Our experimental results demonstrate that FuseBot outperforms X-Ray’s efficiency by more than 40% in terms of the number of actions required for successful mechanical search. Furthermore, in comparison to X-Ray’s success rate of 84%, FuseBot achieves a success rate of 95% in retrieving untagged items, demonst