Understanding, implementing, training and debugging deep end-to-end neural network architectures for various tasks of computer vision. Image classification. Loss functions and optimization. Backpropagation. Convolutional neural networks. Recurrent neural networks for video and image analysis. Object detection and segmentation. Generative vision models.

Principles of computer networks and network protocols; Internet protocol stack with emphasis on application, transport, network and link layers; network edge and network core; client/server and peer-to-peer models; routing algorithms; reliable data transfer; flow and congestion control; protocol design and analysis; network performance metrics; software-defined networks; network programming and distributed applications.

Threats to data privacy and security; methods for privacy-preserving data collection, analysis, and sharing; data anonymization; differential privacy; security and privacy in machine learning; adversarial machine learning; real- world applications and case studies.

Basic linear models for classification and regression; stochastic gradient descent (backpropagation) learning; multi-layer perceptrons, convolutional neural networks, and recurrent neural networks; recent advances in the field; practical examples from machine translation, computer vision; practical experience in programming, training, evaluating and benchmarking deep learning models.

Introduction to cryptographic concepts. Symmetric encryption, the public-key breakthrough, one-way functions, hash functions, random numbers, digital signatures, zero-knowledge proofs, modern cryptographic protocols, multi-party computation. Everyday use examples including online commerce, BitTorrent peer-to-peer file sharing, and hacking some old encryption schemes.

A capstone design course where students apply engineering and science knowledge in a computer engineering design project. Development, design, implementation and management of a project in teams under realistic constraints and conditions. Emphasis on communication, teamwork and presentation skills.

Understanding, implementing, training and debugging deep end-to-end neural network architectures for various tasks of computer vision. Image classification. Loss functions and optimization. Backpropagation. Convolutional neural networks. Recurrent neural networks for video and image analysis. Object detection and segmentation. Generative vision models.

Threats to data privacy and security; methods for privacy-preserving data collection, analysis, and sharing; data anonymization; differential privacy; security and privacy in machine learning; adversarial machine learning; real- world applications and case studies.

Basic linear models for classification and regression; stochastic gradient descent (backpropagation) learning; multi-layer perceptrons, convolutional neural networks, and recurrent neural networks; recent advances in the field; practical examples from machine translation, computer vision; practical experience in programming, training, evaluating and benchmarking deep learning models.

Introduction to cryptographic concepts. Symmetric encryption, the public-key breakthrough, one-way functions, hash functions, random numbers, digital signatures, zero-knowledge proofs, modern cryptographic protocols, multi-party computation. Everyday use examples including online commerce, BitTorrent peer-to-peer file sharing, and hacking some old encryption schemes.

Presentation of research topics to introduce the students into thesis research.

Intensive seminar on selected management topics.

An applied, non-technical introduction to the methods and ideas of Computational Social Sciences. How new online data sources and the computational methods shed new light on old social science questions and ask brand new questions. Some of the ethical and privacy challenges of living in a world of big data and algorithmic decision making.

This course, broadly speaking, is designed to familiarize the student with Python 3 and advanced data analysis techniques. Core programming concepts using Python, which apply to programming more generally, is covered. These include syntax, data types, functions, loops, recursion, and classes and inheritance. Then, database management, creation, manipulation, and visualization concepts are discussed. A brief overview of Bayesian statistics with an emphasis on practical use in the Stan programming language called through Python will be followed by introductions to the most common machine learning methods. This is a demanding course, with the ultimate goal a final project with an original analysis testing one or several hypotheses. No previous programming experience is assumed. However, a good understanding of linear models is required.

Detailed examination of current topics in CSSM

Foundational topics necessary for cyber security, such as basics of programming, computer architecture, operating systems, computer networks, and databases.

Introductory cyber forensics and digital forensics definitions, evidence collection methodologies, data recovery tools, software and hardware tools employed for forensic analysis, evidence reporting procedures and techniques.

Blockchain, distributed consensus, distributed databases, flooding and broadcasting, crypto currencies, security of crypto currencies, blockchain applications, alternative blockchain and crypto currency proposals, smart contracts.

A broad introduction to machine learning covering regression, classification, clustering, and dimensionality reduction methods; supervised and unsupervised models; linear and nonlinear models; parametric and nonparametric models; combinations of multiple models; comparisons of multiple models and model selection.

Introduction to cryptographic concepts. Symmetric encryption, the public-key breakthrough, one-way functions, hash functions, random numbers, digital signatures, zero-knowledge proofs, modern cryptographic protocols, multi-party computation. Everyday use examples including online commerce, BitTorrent peer-to-peer file sharing, and hacking some old encryption schemes.

An introduction to interactive Python and Jupyter Notebooks, Python built-in data structures, conditional statements, loops, functions, strings and basic input/output, basics of data manipulation and visualization with relevant Python libraries, different types of plots, vector/matrix representations, linear algebra operations, probability/statistics operations, data analysis applications

A broad introduction to machine learning covering regression, classification, clustering, and dimensionality reduction methods; supervised and unsupervised models; linear and nonlinear models; parametric and nonparametric models; combinations of multiple models; comparisons of multiple models and model selection.

A broad introduction to machine learning covering regression, classification, clustering, and dimensionality reduction methods; supervised and unsupervised models; linear and nonlinear models; parametric and nonparametric models; combinations of multiple models; comparisons of multiple models and model selection.