Advanced Machine Learning

ADVANCED MACHINE LEARNING 

  • Instructor: Arti Ramesh
  • Open year round
  • Delivery: Self-paced online, pre-recorded video lectures in addition to self-assessment quizzes (not graded) and final exam (graded).
  • Credentials: The students who successfully complete the course by passing the final exam will receive the Advanced Machine Learning digital badge. A printable 绿帽社 certificate will also be available for successful participants.
  • Who can take this course: This course is open to all engineers, professionals, faculty and students.

ABOUT THE COURSE

This course will provide a solid introduction to machine learning. In particular, upon successful completion of this course, students will be able to understand, explain and apply key machine learning concepts and algorithms, including:

  • Probability review
  • Point Estimation Techniques
  • Perceptrons
  • Neural Network model
  • Support Vector Machines
  • K Nearest Neighbors
  • Machine-learning learning and inference procedures and concepts such as maximum likelihood estimation, gradient descent, backpropagation, Lagrange for solving constrained optimization problems, bias-variance tradeoff, and curse of dimensionality

LEARNING OUTCOMES

At the end of the course, students will be able to

  • Understand point estimation techniques for estimating parameters of machine learning models.
  • Understand and apply more advanced machine-learning algorithms to particular scenarios such as perceptrons, neural network models, support vector machines, and k-nearest neighbors.
  • Understand subtleties and application scenarios for different classification algorithms discussed above.
  • Explain and apply machine-learning concepts such as regularization, overfitting, maximum likelihood estimation, gradient descent, backpropagation, Lagrange for solving constrained optimization problems, bias-variance tradeoff, and curse of dimensionality to design efficient machine learning models.

ABOUT THE INSTRUCTOR

Arti Ramesh is an assistant professor in the School of Computing at 绿帽社. She received her PhD in Computer Science from the University of Maryland, College Park.

Her primary research interests are in the field of machine learning, data mining, and natural language processing, particularly statistical relational models and deep learning. Her research focuses on building structured, fair and interpretable models for reasoning about interconnectedness, structure, and heterogeneity in networked data.

She has published papers in peer-reviewed conferences such as IJCAI, AAAI, ACL, WWW, ECAI, and DSAA. She has served on the TPC/reviewer for notable conferences such as ICML, IJCAI, AAAI, NIPS, SDM, and EDM. She has won multiple awards during her graduate study including the Ann G. Wylie Dissertation Fellowship, outstanding graduate student Dean鈥檚 fellowship, Dean鈥檚 graduate fellowship, and the Yahoo Scholarship for the Grace Hopper Conference.

COURSE FEES

  • $325: Standard/Industry rate
  • $210: BU Faculty/Staff and Alumni
  • $135: BU Students and High School Students
  • $35: Retake fee Students (requires proof of previous registration)
  • $50: Retake fee Non-Students (requires proof of previous registration)

PAYMENTS

Payment is made at the time of registration. For questions, contact the Office of Industrial Outreach at wtsnindy@binghamton.edu.

CANCELLATIONS AND REFUNDS

Please note our cancellation and refund policy: All cancellations must be received in writing (email) to the Office of Industrial Outreach. All refunds will be assessed a 10% administrative fee. No refunds for cancellations or non-attendance will be given after you have started the course.  Submit your cancellation request to EMAIL: wtsnindy@binghamton.edu.

If the course is canceled, enrollees will be advised and receive a full refund.