Neural Networks and Deep Learning
Columbia University course ECBM E4040
Zoran Kostic, Ph.D., Dipl. Ing., Associate Professor of Professional Practice, zk2172(at)
Electrical Engineering Department, Columbia University in the City of New York

Course in a nutshell: 

    Theoretical underpinnings and practical aspects of Neural Networks and Deep Learning. Focus on applications and projects.

To be able to register for the course, students need to register into the SSOL waitlist and populate this form -> E4040 student questionnaire (use CU email). Direct registration (without SSOL waitlist) is not possible. SSOL should allow students from all Columbia schools, both undergraduate and graduate, to get onto the SSOL waitlist.

Bulletin Description:
  • Developing features & internal representations of the world, artificial neural networks, classifying handwritten digits with logistics regression, feedforward deep networks, back propagation in multilayer perceptrons, regularization of deep or distributed models, optimization for training deep models, convolutional neural networks, recurrent and recursive neural networks, deep learning in speech and object recognition.
Course: Open to Columbia students.
  • Fall 2017: TBA
  • Fall 2016: Fridays 10:10-12:20.
  • Prerequisites: BMEB W4020 or BMEE E4030 or ECBM E4090 or EECS E4750 or COMS W4771 or an equivalent. Basic programming.
  • Provides a straightforward introduction to neural networks.
  • Focuses on the intuitive understanding of deep learning.
  • Enables the further exploration of key concepts in deep learning.
  • Analytical study and software design 
  • Lectures:
    • Presentation of material by instructors and guest lecturers
  • Homeworks:
    • Combination of analytical and programming assignments
  • Projects:
    • Team-based
    • Students with complementary backgrounds
    • Significant design
    • Reports and presentations to Columbia and NYC community
    • Best could qualify for publications and/or funding
  • Industry participation:
    • Project definition and sponsoring
    • Weekly presentations
    • Interaction with students through mentoring
Project Areas
  • Medical
  • Autonomous cars
  • Environmental
  • Smart cities
  • Physical data analytics
  • Other
 Books, Tools and Resources
Course sponsored by equipment and financial contributions of:
  • NVidia GPU Education CenterAWS Educate, Google Cloud, IBM Bluemix,  Atmel, Broadcom (Wiced platform); Intel (Edison IoT platform), Silicon Labs.