Research

Closed-loop software and hardware platforms driving chemical discovery through automated hypothesis generation, refinement, validation, and revision, resulting in predictive chemical kinetic models.

Computational imaging

Human behavior in the context of organizational service interactions. Big data and automation tools are used to objectively analyze emotion and behavior of participants in online conversations.

Proteomics; Cancer Vaccines; Antigen Processing and Presentation; Big data of proteomics and peptidomics; Bioinformatics of proteomics and mass spectrometry.

Applied biomechanics and investigation of the interaction of mechanics, biology, and structure of musculoskeletal joint pathologies. Implementing smart wearable technologies that record large data sets of bio-signal motion data.

Distributed and Scalable Deep Learning; Deep Learning for Personal Medicine; Randomness in Deep Learning; Analytics of Rapid Data Streams; Complex Event Processing (CEP); Internet of Things and Smart Systems; Privacy Preserving; Cyber Security; Cloud Management

Nanotechnology, cancer, Parkinson's disease, AI

Schema Matching; Entity Resolution; Semantic Integration of Data Resources; Business Process Management; Temporal Databases and Temporal Evolution of Databases.

Service-Engineering of large operations (e.g. hospitals / emergency-departments, call / contact-centers, courts, …); Operations research; Statistics; Queueing science & theory; Control theory; Data- and process-mining.

My research focuses on AI and machine learning, with an emphasis on robotics applications. My long term goal is to bring robots into human-centered domains such as homes and hospitals. Towards this goal, some fundamental questions need to be solved, such as how can machines learn models of their environments that are useful for performing tasks, and how to learn behavior from interaction in an interpretable and safe manner. Most of my work falls under the framework of reinforcement learning, and its connections to representation learning and planning.

We study fundamental epigenetics processes affecting gene expression and regulation by using bioinformatics, generating pipelines, and experimental biology.

Computer Vision, Computer Graphics, Machine Learning, Visualization.

Enviromatics; machine learning methods and mathematical for natural complex environments; hydro-informatics; atmospheric-informatics; precise agriculture; structural health; smart infrastructure systems and connected transportation.

Deep Neural Network representation learning, Machine Learning, Computer Vision, Geometric Deep learning, Algorithms for efficient training and inference of Deep Neural Networks.

Deep Learning, i.e., neural networks: understanding them theoretically (e.g., their implicit bias) and improving them (e.g., their resource efficiency and speed during training and inference).

Mechanobiology of cancer and wounds. Early-prognosis of cancer metastasis. Wound healing and prevention. Experiments, Finite element modeling, machine learning.

Optimal designs for clinical trials, Regression, Semi-supervised learning, Statistical theory.

Recording and analysis of nerve cell populations in the brain during tasks of spatial learning and memory, using electrode probes, tetrodes, and calcium-imaging.

Conceptual Modeling, Systems Eng. and Modeling, Systems Architecture, Enterprise Systems Modeling; Object-Process Methodology; Ontologies; Software Development Methodologies, Semantic Web; Systems Biology, Robotics.

Computational biology; Clinical informatics

Program Synthesis, Machine Learning for Programming Languages, Neuro-Symbolic Models, Program Analysis

Automated Planning, Robotics, Artificial Intelligence.

Establishing and analyzing large-scale clinical and biological/genetic bio-banks and databases to study disease etiology and clinical behavior, especially with regards to malignancies.

Service Engineering/Service Operations; Behavioral Operations; Queueing Networks and Approximations; Healthcare and Call-center Operational Design.

Image processing and computer vision, with strong focus on mathematical models related to calculus of variations and nonlinear spectral theory.

Nano and micro-fabricated surfaces for cell biology research; Mechanobiology of Cells.

Nano-array devices for screening, diagnosis and monitoring of disease, nanomaterial-based chemical (flexible) sensors, electronic skin, breath analysis, volatile biomarkers, and cell-to-cell communication.

Implications of quantum mechanics on future technology; Algorithms to automate research in fundamental science and in mathematics; Fundamentals of light-matter interactions; Probing materials with ultrafast electrons and photons.

Algorithmic game theory; Theory of computation; Optimization; AI; Internet economics; Market design; Auctions.

InterArray processing, signal processing, deep learning, analysis and modeling of acoustic signals, speech enhancement, noise estimation, source localization, blind source separation, system identification and adaptive filtering.

Genomics and epigenetics and cardiac imaging.

The Artificial Intelligence in Medicine Laboratory (AIMLab.) researches innovative pattern recognition algorithms to exploit the information encrypted within large datasets of physiological time series.

Data Science Methods: Spectral Total Variation Techniques; Biomedical Engineering: PET/CT and SPECT/CT data fusion, characterization, quantitation, artifact removal, optimization of clinical imaging protocols.

Environmental quality driven urban design, Generative urban design, Zero energy buildings and districts, Performance-based design using digital tools, Environmental workspace design, Passive low carbon design strategies

Computational Cancer Genomics; Our lab addresses emerging challenges in computational cancer genomics by developing and applying computational methods for cancer data analysis.

Machine Learning in Healthcare, Chemoinformatics, Data Mining, Natural Language Processing, Information Retrieval, Knowledge Discovery, Machine Learning, Artificial Intelligence, Digital Healthcare

The psychology of AI, Answers to human related questions with big data, Consumer behavior as reflected in big data.

Computer Vision, e.g., data generation, multi-label classification; Machine Learning with focus on designing and training efficient and effective Neural Networks; Tactile sensing and haptic feedback

Using microscopy technologies, we capture the dynamic function of cell nuclei and neural circuits as well as their 3D nano-scale structure. Via machine learning, we extract the information of interest from these datasets, linking biological structure to function.

Data models; Sparse Representations – Theory and Practice and their Connection to Deep-Learning; Inverse Problems in Signal and Image Processing; Image Denoising; Graph-Based Signal Processing; Patch-Based Image Processing; Super-Resolution

Modeling and understanding the geometry of shapes, differential geometry, architectural geometry, remeshing for fabrication, numerical optimization and harmonic analysis, animation, fluid simulation.

Control policies that facilitates learning and sim2real transfer with applications to robot assembly and legged locomotion; Invasive and non-invasive Brain Machine Interfaces (BMIs) and error related processing;

Improving patient care and outcome through better characterization of the underlying physiological and structural factors in human diseases by developing novel deep-learning-based methods for MRI acquisition and analysis.

The Lab focuses on T cell immunology in the interface between cancer and autoimmunity, with a particular interest in chemokine-chemokine receptor interactions. The lab develops unique strategies for cancer immunotherapies and for restraining autoimmunity.

Modeling and predicting human behavior and social dynamics; Learning to support human decision-making; Training for human objectives and with humans in the loop; Implications of deploying predictive models in social contexts.

3D genomics, nuclear organization, computational biology, epigenetics, classical and deep machine learning, probabilistic models.

Artificial Intelligence; Human-Computer Interaction; Intelligent User Interfaces; Explainable AI.

Theoretical neuroscience. How complex systems adapt to their environment? Such systems include brains, cancer cells, and artificial neural networks.

I seek to deeply understand and to rigorously address the computational challenges that arise when planning for robots. My research, lying at the intersection of Computer Science and Robotics, is motivated by the key insight that in order to address these challenges, traditional Computer Science algorithms, tools and paradigms need to be revisited. This requires (i) understanding and analyzing the unique domain-specific computational challenges in robotic planning and, subsequently (ii) developing algorithms to address these challenges to provide the robotics community foundational tools to solve real-world problems. For additional details, see my research statement.

Predicting human decision making; Mining behavioral data; behavioral economics; behavioral decision making; human learning processes; behavioral mechanism design; behavioral public policy.

Biostatistics and clinical trial design and analysis, experimental design, inference for stochastic processes, classification and regression modelling.

When facing challenging tasks in computerized and daily tasks, people must engage in mental effort management. Professor Ackerman studies factors that drive cognitive biases and waste of thinking time.

Game theory, Economic theory, Privacy.

I am interested in understanding and mitigating the negative effects of strategic behavior. Mainly by people interacting via large systems, e.g. congestion in networks or biased group decisions.

Natural Language Processing (NLP). Out-of-distribution generalization in NLP (e.g. cross-language and cross-domain learning); NLP for social, behavioral and health science; Causality and model interpretation.

Computer vision, graphics, Geometric machine learning and big data, computational medicine and biometry, applied metric and differential geometries.

Mathematical foundations of deep learning, graph neural networks, geometric deep learning, explainable AI.

Information processing, learning and control in natural and artificial systems, reinforcement learning, lifelong learning, multi agent learning, the perception action cycle.

Geometry-based Data Analysis & Modeling; Signal Processing; Applied Harmonic Analysis; Diffusion Geometry; Biomedical Signal Processing; Computational Neuroscience.

Developing and applying advanced machine-learning and experimental tools at the frontiers of biomedicine with a specific focus on antimicrobial multi-drug therapy.

Geodata science, methods of interpretation, mining, and integration of crowdsourced content to augment and develop location-based services and smart mapping infrastructures. Spatial-cognition, navigation, and the built-environment.

Multi-agent AI, multi-robot systems, collaborative AI, multi-agent environment design, integrated task and motion planning for robotics, and multi-agent reinforcement learning.

Performing logic using memory cells to build the memristive memory processing unit (mMPU), mixed-signal circuits, RF circuits, neuromorphic computing, cytomorphic systems, deep learning accelerators, internet-of-things, and hardware security.

AI and machine learning, reinforcement learning and planning; learning, optimization and control under uncertainty, Multi-agent systems, Optimization of large scale problems, application of machine learning to a variety of problems: power grids, communication networks, etc.

Robust and adaptive optimization; Data-driven optimization; Algorithms for nonconvex and mixed-integer optimization; Optimization applications in: energy, inventory systems, estimation and control, statistics and healthcare.

Surgical Data Science, Computer Vision, Automatic Surgical Workflow Analysis, , Automatic Assessment of Competency-Based Medical Education in Surgery and Anesthesiology

Continuous Optimization: Theory and Algorithms, development and analysis of Optimization Methods for large-scale optimization problems, Applications of Optimization Methods in Machine/Deep Learning.

Neuro-AI: the intersection between neuroscience, machine learning and theoretical methods.

Theoretical & practical aspects of machine learning. Mathematical solutions to real-life problems demonstrating non-traditional statistical behavior.

Relating brain functional / structural patterns to children’s abilities (reading, language, memory, attention). Modeling physiological datasets (speech, heart rate, eye-movement, brain markers etc) for intervention and diagnostic tools.

Machine learning; causal inference; machine learning for healthcare; deep learning.

The intersection of probabilistic perception and inference, learning, and planning under uncertainty, both for single and distributed multi-agent autonomous systems.

Automatic diseases classification, Cell Biophysics, Heart rate variability analysis, Mobile health devices, Prediction and detection of atrial and ventricular fibrillation, Sinoatrial node cell activity.

Survival analysis, Empirical processes, Machine learning, Semiparametric models.

Research centers around the theory and practice of statistical inference and machine learning, focusing on the reliability, robustness, and interpretability of modern data-driven algorithms.

Design computation, computer aided design and fabrication.

Computational imaging, fluorescence microscopy, cellular imaging, 3D imaging, super-resolution microscopy, wavefront shaping

Higher-level cognition; Cognitive complexity; Creativity; Network science in cognitive science; Network neuroscience; Clinical cognitive Networks; Cognitive search

Natural language processing; machine learning for language understanding and generation; neural network representations; interpretability and robustness of machine learning models.

Keshet's research concerns both machine learning and the computational study of human speech and language. His work on speech and language concentrates on speech processing, automatic speech recognition, speaker recognition, automating laboratory phonology, and pathological speech. His research on machine learning focuses on core machine learning and deep learning algorithms, specifically, that capture the structure of complex tasks, such as automatic speech recognition. But also - how to make them reliable and trustworthy.

Storage devices, systems; Reliable data distribution in networks; Coding theory, Data compression.