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.

Web page link.

To be able to register for the course, students need to (1) register into the SSOL waitlist and (2) populate this form -> E4040 student questionnaire (use CU email). Direct SSOL registration (without SSOL waitlist) is not possible.  Registration decisions will be a function of student background, program/major and potential limitations on the classroom size.

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: Fridays 10:10-12:20.
  • 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
2016 Projects
  • Striving for Simplicity: The All Convolutional Net
  • A Combined Semi-supervised Learning mechanism for Video Data via Deep Learning
  • A Neural Algorithm of Artistic Style
  • Adieu features? End-to-end speech emotion recognition using a deep convolutional recurrent network
  • Colorful Image Colorization
  • Deep Networks with Stochastic Depth
  • Highway Networks
  • Image Super-Resolution Using Deep Convolutional Networks
  • Learning to Protect Communications with Adversarial Neural Cryptography
  • Singing Voice Separation from Monaural Recordings Using Deep
  • Recurrent Neural Networks
  • Spatial Transformer Networks
  • Spoken Language Understanding Using Long-Short Term Memory Neural Networks
  • Striving for Simplicity: The All Convolutional Net
  • Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
2017 Projects
  • TBD
Course sponsored by equipment and financial contributions of:
  • NVidia GPU Education Center, Google Cloud, IBM Bluemix, AWS Educate, Atmel, Broadcom (Wiced platform); Intel (Edison IoT platform), Silicon Labs.