Research

Network routing, survivability, QoS provisioning, wireless networks, the application of game theory to computer and power networks, blokchains, the application of machine learning to network protocols.

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

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.

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

" Safety guarantees to deep learning by leveraging formal methods, such as analysis and synthesis."

The theory and applications of efficient network and system management, in particular, concentrating on cloud resource management, NFV, SDN, TE, and network aware services.

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

Information and coding theory with applications to non-volatile memories, associative memories, data storage and retrieval, distributed storage, privacy, and DNA storage.

Using machine learning in datacenter networks and high-performance routers, e.g., for congestion control, flow classification, and buffer management.

Machine Learning and Optimization.

Machine Learning and Statistics, Combinatorial Optimization and Approximation Algorithms, Algorithmic Dimension Reduction and Applications, Complexity.

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

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.

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

Caching, network monitoring, stream processing, reliable distributed systems, high-availability and fault-tolerance, blockchains, cloud computing, wireless mobile ad hoc network

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.

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

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.

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.