Omar Shehab PhD defense: Solving Mathematical Problems in Quantum Regime, 7/7

dwave_quantum-chip

Ph.D. Dissertation Defense
Computer Science and Electrical Engineering

Solving Mathematical Problems in Quantum Regime

Omar Shehab

2:00pm Thursday, 7 July 2016, ITE 325b

In this dissertation, I investigate a number of algorithmic approaches in quantum computational regime to solve mathematical problems. My problems of interest are the graph isomorphism and graph automorphism problems, and the complexity of memory recall of Hopfield network. I show that the hidden subgroup algorithm, quantum Fourier sampling, always fails, to construct the automorphism group for the class of the cycle graphs. I have discussed what we may infer for a few non-trivial classes of graphs from this result. This raises the question, which I have discussed in this dissertation, whether the hidden subgroup algorithm is the best approach for these kinds of problems. I have given a correctness proof of the Hen-Young quantum adiabatic algorithm for graph isomorphism for cycle graphs. To the best of my knowledge, this result is the first of its kind. I also report a proof-of-concept implementation of a quantum annealing algorithm for the graph isomorphism problem on a commercial quantum annealing device. This is also, to the best of my knowledge, the first of its kind. I have also discussed the worst-case for the algorithm. Finally, I have shown that quantum annealing helps us achieve exponential capacity for Hopfield networks.

Committee: Drs. Samuel J Lomonaco Jr. (Chair), Milton Halem, Yanhua Shih, William Gasarch and John Dorband

Travel grants for students to attend 2016 Grace Hopper Conference

Google will fund travel grants to the 2016 Grace Hopper Celebration of Women in Computing Conference (GHC) which takes place in Houston, Oct 19-21, 2016. The GHC is the world’s largest gathering of women technologists and offers many valuable resources to students and academics alike, from a Student Opportunity Lab to tracks specifically designed to educate and inspire faculty. Its career fair, one of the largest in the U.S., earns a 97% satisfaction rate from our student survey respondents.

University students and industry professionals in the US and Canada who are excelling in computing and passionate about supporting women in tech can apply for a travel grant to attend the 2016 Grace Hopper conference. Sponsorship includes: conference registration, round trip flight to Houston, TX, arranged hotel accommodations from October 18-22, $75 USD reimbursement for miscellaneous travel costs and a fun social event with your fellow travel grant recipients on one of the evenings of the conference.

Apply by Sunday, July 10 using this online form. The Grace Hopper Travel Grant recipients will be announced by July 27th.

PhD defense: Z. Wang, Learning Representations and Modeling Temporal Signals

Computer Science PhD Dissertation Defense

Learning Representations and Modeling Temporal Signals:
Symbolic Approximation, Deep Learning, Optimization and Beyond

Zhiguang Wang

1:00pm Tuesday, 31 May 2016, ITE 325, UMBC

Most real-world data has a temporal component, whether it is measurements of natural or man-made phenomena. Specifically, complex, high-dimensional and noisy temporal data are often difficult to model because the intrinsic temporal/topographic structures are highly non-linear, which makes the learning and optimization procedure more complicated. This talk will cover three correlated but self-contained topics to address the problem of representation learning in time series, deep learning optimization, and unsupervised feature learning.

First, I will show how to incorporate ideas from symbolic approximation with simple NLP techniques to represent and model temporal signals. To improve the symbolic approximation to model signals as words, we build a time-delay embedding vector (AKA skip gram) to extract the dependencies at different time scales, which yields state-of-the-art classification performance with a bag-of-patterns and vector space model. A non-parametric pooling/weighting scheme is proposed to extend the methods to multivariate signals

Second, I will show how to encode signals as images to learn and analyze them with deep learning methods. The Gramian Angular Field (GAF) and Markov Transition Field (MTF), as two novel approaches to encode both multi-scale spatial correlation and first order Markov dynamics of the temporal signals as images, are proposed. These visual representations are proved to work well in both visualizations by humans and pattern recognition using deep learning approaches. This work yields state-of-the-art algorithms for temporal data classification and imputation.

Finally, deep learning in image recognition (e.g. pictures or GAF/MTF images) involves high-dimensional non-convex optimization. Such optimization is generally intractable. However, I show how to use a set of exponential form based error estimators (NRAE/NAAE) and learning approaches (Adaptive Training) to attack the non-convex optimization problems in training deep neural networks. Both in theory and practice, they are able to achieve optimality on accuracy and robustness against outliers/noise. They provide another perspective to address the non-convex optimization problem (especially saddle points) in deep learning.

Committee: Tim Oates (Chair), Matt Schmill (Miner & Kasch), Hamed Pirsiavash, Yun Peng, Kostas Kalpakis

Microsoft Student Partners program

Microsoft Student Partners (MSPs) are student technology leaders, empowered to build Microsoft communities on their campus and share their deep knowledge and passion for technology with their fellow classmates.  See here for more information. Apply by 15 July 2016.

UMBC students demonstrate smartphone applications, 12:30-2:30 Tue 5/10

mobile_class_csee

cordova
7919_New Faculty 2009 Nilanjan Banerjee Computer Science and Computer Engineering

Student groups drawn from two UMBC classes will demonstrate twelve mobile applications they developed as projects from 12:30 to 2:30 on Tuesday, 10 May 2016 in the UC Ballroom. Pizza will be provided.

The projects are a result of an innovative collaboration between a computer science class lead by Professor Nilanjan Banerjee (CMSC 678 Mobile Computing) and a visual arts class lead by Professor Viviana Chacon (ART 434 Advanced Interface Design).

The two faculty were awarded a grant from the fall 2015 round of the Hrabowski Fund for Innovation competition to develop and evaluate the collaboration between the two courses. The classes held regular joint sessions and each project group comprised students from both Engineering and Visual Arts.

In ART 434 Prof. Cordova concentrated on the visual experience of the interface in mobile and desktop applications, while in CMSC 628 Prof.  Banerjee provided the tools necessary to design and implement mobile applications.  Specific mobile development topics such as user interface design and implementation, accessing and displaying sensor and location data, and mobile visual design were co-­‐taught by both instructors.  Teams comprising Engineering and Visual Arts students designed and built mobile applications for local clients in Baltimore and Washington DC area.

poster describing the event has brief descriptions of the twelve class projects.

NSF CyberCorps: Scholarship For Service, May 15 deadline

UMBC undergraduate and graduate students interested in cybersecurity can apply for an Federal CyberCorps: Scholarship For Service scholarship by 15 May 2016. This application deadline will be the last one under the current NSF grant, which ends August 2017.

The Federal CyberCorps: Scholarship For Service program is designed to increase and strengthen the cadre of federal information assurance professionals that protect the government’s critical information infrastructure. This program provides scholarships that may fully fund the typical costs incurred by full-time students while attending a participating institution, including tuition and education and related fees. Participants also receive stipends of $22,500 for undergraduate students and $34,000 for graduate students.

Applicants must be be full-time UMBC students within two years of graduation with a BS or MS degree; a student within three years of graduation with both the BS/MS degree; a student participating in a combined BS/MS degree program; or a research-based doctoral student within three years of graduation in an academic program focused on cybersecurity or information assurance. Recipients must also be US citizens or permanent residents; meet criteria for Federal employment; and be able to obtain a security clearance, if required.

For more information and instructions on how to apply see the UMBC CISA site (use old application form, and be sure to include the cover sheet).

talk: Down the rabbit hole: An Android system call study, 10:30 Mon 3/28

android-security

Down the rabbit hole: An Android system call study

Prajit Kumar Das

10:30 am, Monday, March 28, 2016 ITE 346

App permissions and application sandboxing are the fundamental security mechanisms that protects user data on mobile platforms. We have worked on permission analytics before and come to a conclusion that just studying an app’s requested access rights (permissions) isn’t enough to understand potential data breaches. Techniques like privilege escalation have been previously used to gain further access to user and her data on mobile platforms like Android. Static code analysis and dynamic code execution may be studied to gather further insight into an app’s behavior. However, there is a need to study such a behavior at the lowest level of code execution and that is system calls. The system call is the fundamental interface between an application and the Linux kernel. In our current project, we are studying system calls made by apps for gathering a better understanding of their behavior.

HackUMBC 24 -hour student hackathon, 5-6 March 2016 at UMBC

HackUMBC2016

HackUMBC is a 24 hour student hackathon that will take place on Saturday and Sunday, March 5-6, 2016 at UMBC. It’s an opportunity to learn new skills, make friends, create your wildest idea, and share it with the world. Build an app, a website, a robotic arm, a game, anything. It’s free and food, beverages, swag, workspaces, and sleeping areas will be provided. All undergraduate, graduate, and high school students are welcome, but pre-registration is required. Get more information and apply at https://hackumbc.org/.

PhD defense: Infrastructure-less Group Data Sharing using Smart Devices

Ph.D. Dissertation Defense

Infrastructure-less Group Data
Sharing using Smart Devices

Ahmed Shahin

2:30 Tuesday, 8 December 2015, ITE-346

Advances in pervasive communication technology have enabled many unconventional applications that facilitate and improve the safety and quality of life in modern society. Among emerging applications is situational awareness where individuals and first-responders receive timely alerts about serious events that could have caused the interruption of the services provided by the communication infrastructure such as cellular networks, Wi-Fi hotspots, etc. Another example is when exchanging road conditions between peer-to-peer networked vehicles without the involvement of roadside units. The popularity of smart portable devices such as iPhone and Android powered phones and tablets has made them an attractive choice that can play a role in the realization of these emerging applications. These devices support multiple communication standards and thus enable Device-to-Device (D2D) data exchange at an increased level of convenience. By using technologies such as Bluetooth, Wi-Fi ad-hoc mode and Wi-Fi Direct, these devices are able to communicate without the need for any communication infrastructures. In addition, many of these devices are equipped with sensors that can provide a wealth of information about the surroundings once their readings are aggregated.

However, most existing protocols for data sharing among devices either require an internet connection, which may not be available and may incur extra costs in some cases, or suffer from the device’s operating system limitations. Actually there is no existing solution that allows a set of devices to start sharing data dynamically without forcing the users to apply an elaborate procedure for setting up a group. These shortcomings render existing solutions unsuitable for emergency cases. In this dissertation proposal, we tackle such a problem by developing a framework for enabling data exchange in a cost-effective and timely manner through the establishment of peer-to-peer links among smart devices. In addition, our framework opts to minimize the user required interaction for setting up a connection and overcome the limitations of the operating system.

Our framework consists of a set of protocols for group data exchange using Wi-Fi Direct on Android devices. First we present an Efficient and Lightweight protocol for peer-to-peer Networking of Android smart devices over Wi-Fi Direct (ELN). ELN main goal is to overcome the Wi-Fi Direct support limitations in Android, thus allowing the devices in one Wi-Fi Direct group to communicate together. The ELN protocol is validated by implementing a group chatting application. In addition, we present a protocol for Alert Dissemination using Service discovery (ADS) in Wi-Fi Direct. ADS uses the service discovery feature of Wi-Fi Direct for distributing alerts to nearby devices without requiring any prior connections and thus avoids the setup delay in creating Wi-Fi Direct groups and the limitations of multi-group connectivity in Android. ADS is validated by implementing a hazard propagation application for Android. Finally, we present an Efficient Multi-group formation and Communication (EMC) protocol for Wi-Fi Direct. EMC exploits the battery specifications of the devices to qualify potential group owners and enable dynamic formation of efficient groups. Moreover, EMC allows data exchange between different Wi-Fi direct groups. Part of our implementation of EMC in Android involves the modification of the Android source code to allow multi-group support. A chat application is developed to validate EMC.

To complete the dissertation, we plan to extend EMC by replacing the static assignment of devices’ addresses in our current implementation with an IP address negotiation protocol that runs before creating groups. Such an extension would give greater flexibility in adapting EMC. In addition, we plan to define some criteria for selecting proxy members in order to allow maximum coverage and allow the D2D communication to span a larger geographical area. In addition, we will develop a simulator to do large scale testing for the proposed framework. Finally, we would like to explore the use of dual transceivers in order to increase the robustness of D2D connections when the wireless channels are subject to varying level of interference; particularly we like to investigate the integration of Bluetooth Low Energy within our framework to enable group membership of nodes that do not have Wi-Fi Direct or suffer interference that makes the Wi-Fi Direct links unstable.

Committee: Drs. Mohamed Younis (Chair), Charles Nicholas, Chintan Patel, Tinoosh Mohsenin

MS defense, Budhraja: Neuroevolution-Based Inverse Reinforcement Learning

kanran

M.S. Thesis Defense

Neuroevolution-Based Inverse Reinforcement Learning

Karan K. Budhraja

9:00am Wednesday, 2 December 2015, ITE 346

Motivated by such learning in nature, the problem of Learning from Demonstration is targeted at learning to perform tasks based on observed examples. One of the approaches to Learning from Demonstration is Inverse Reinforcement Learning, in which actions are observed to infer rewards. This work combines a feature based state evaluation approach to Inverse Reinforcement Learning with neuroevolution, a paradigm for modifying neural networks based on their performance on a given task. Neural networks are used to learn from a demonstrated expert policy and are evolved to generate a policy similar to the demonstration. The algorithm is discussed and evaluated against competitive feature-based Inverse Reinforcement Learning approaches. At the cost of execution time, neural networks allow for non-linear combinations of features in state evaluations. These valuations may correspond to state value or state reward. This results in better correspondence to observed examples as opposed to using linear combinations.

This work also extends existing work on Bayesian Non-Parametric Feature construction for Inverse Reinforcement Learning by using non-linear combinations of intermediate data to improve performance. The algorithm is observed to be specifically suitable for a linearly solvable non-deterministic Markov Decision Processes in which multiple rewards are sparsely scattered in state space. Performance of the algorithm is shown to be limited by parameters used, implying adjustable capability. A conclusive performance hierarchy between evaluated algorithms is constructed.

Committee: Drs. Tim Oates, Cynthia Matuszek and Tim Finin

1 2 3 4 5 6 36