First Day to Apply for Spring 2024 Short Term Advance

Advances in AI Safety, Security, and Artificial Immune Systems. Please join us in our collective journey to shape the future of AI that prioritizes safety, ethics, and the betterment of humanity. We will create a global community that fosters AI advancements that benefit all while minimizing potential risks.Dates / Time / LocationDecember 4th-5th, 2023Florida Atlantic University777 Glades RoadBoca Raton,FLS.E. Wimberly LibraryGruber AI Sandbox (LY-103)View the full programhttps://openais.ai/2023-symposiumPDF of full programQuestions?For more information, please email aisconference2023@gmail.com

The portion of the exhibition that is in the Jaffe Book Arts Gallery is available for viewing during our regular hours: Monday to Friday, 10 a.m. to 4 p.m. Learn more here.

Get ready for a showdown! Join us for race day as students showcase their engineering projects on December 5th, from 10 am to 4 pm at EE Gangal Hall. Don't miss the chance to witness these innovative designs as these skilled builders compete in a race with the cars they've meticulously crafted!

December 5, 2023, SE43 - room 215, 10 am + Zoom (click here)Speaker: Dominic Gold, Florida Atlantic UniversityTitle: TDA-Preprocessing Yields Quantifiable Efficiency Gains in Privacy-Preserving ML ModelsAbstract: Computational tools grounded in algebraic topology, known collectively as topological data analysis (TDA), have been used for dimensionality-reduction to preserve salient and discriminating features in data. TDA's flagship method, persistent homology (PH), extracts distinguishing shape characteristics from the data directly and provide inherent noise-tolerance and compact, interpretable representations of high-dimensional data that are amenable to well-established statistical methods and machine learning (ML) models; this faithful but compressed representation of data motivates TDA's use to address the complexity, depth, and inefficiency issues present in privacy-preserving, homomorphic encryption (HE)-based ML models through ciphertext packing---the process of packing multiple encrypted observations into a single ciphertext for Single Instruction, Multiple Data (SIMD) operations.By investigating several TDA featurization techniques on the MNIST digits dataset using a logistic regression (LR) classifier, we demonstrated that the TDA methods chosen improves encrypted model evaluation with a 10-25 fold reduction in amortized time while improving model accuracy up to 1.4% compared to naive reductions that used downscaling/resizing. The developed technique also has implications for multiclass classification by sending multiple model classifications in a single packed ciphertext to reduce the communication overhead between the Client and Server, potentially avoiding restriction to a binary classification (as done in past HE-ML literature for secure classification of MNIST digits).Biography: Dominic Gold is a 6th-year graduate teaching assistant at Florida Atlantic University who studies both cryptography and data science, with his main interest in secure/privacy-preserving machine learning on encrypted data. The intersectionality of his research in homomorphic encryption and topological data analysis shows promising implications for research in both fields, with his work in cryptography recognized by venues such as USENIX and ACM CCS. The ultimate goal of his work is to enable real-time predictions on encrypted biomedical data to improve both the reliability, security, and equitability of healthcare systems.Zoom (click here)Meeting ID: 878 9825 0483 Passcode: gHJF6gAll are cordially invited.

Mathematics of Data ScienceWilliam E. Hahn, Ph.D.Office: Wimberly Library, Room 103 (Sandbox)Email: whahn@fau.eduCourse Objectives/Student Learning Outcomes1. Understand the fundamentals of neural networks and deep learning algorithms2. Learn various methods used to construct, train, evaluate and deploy mathematical models3. Analyze different types of input data including image data4. Utilize Python libraries such as PyTorch for building data science notebooksCourse Number: MAP-2192CRN: 14640Credits: 3 credits

Join Odelia Schwartz, Ph.D., Associate Professor of Computer Science, University of Miami, for a presentation on understanding contextual effects in the visual brain and artificial systems.In-person: General Classroom South (GS-2), Room 117, Boca Raton CampusCan't make it in person? Join with Zoom.Meeting ID: 814 2056 2682Passcode: 3x6O4eHosted by Summer Sheremata, Ph.D., FAU Stiles-Nicholson Brain InstituteFor more information, contact Lindsay Montgomery at lmontgomery@fau.edu.