ECBM E6040 Neural Networks and Deep Learning
Course Benefits
| 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. |
Professor Lazar
| Interests in Computational, Systems and Theoretical Neuroscience In Silico: Neural Computing Engines and NeuroInformation Processing Machines. In Vivo: Reverse Engineering the Fruit Fly Brain. In Silico: The Digital Fruit Fly Brain. |
||
| Further information about the instructor is available under URL: http://www.ee.columbia.edu/~aurel. |
Applicable Degree Programs
Most courses 4000-level and above can be credited to all degree programs. All courses are subject to advisor approval.
Lecturer: | Professor Aurel A. Lazar | |
Office hours: | Mondays, 4:00 PM - 6:00 PM, EST, Room 819 CEPSR | |
E-mail address: | aurel "at" ee.columbia.edu | |
Class Web Site: | Offered by CourseWorks | |
TA: | Konstantinos Psychas | |
Office hours: | TBA | |
E-mail address: | kp2547 "at" columbia.edu | |
Day and Time: | Tuesdays, 7:10 PM - 9:40 PM | |
Class Location: | 501 Northwest Corner Building | |
Credits for course: | 3 points | |
Prerequisites | BMEB W4020 or BMEE E4030 or ECBM E4090 or ELEN E4750 or COMS W4771 or the equivalent. | |
Description: |
Developing features and internal representations of the world, artificial neural networks, classifying handwritten digits with logistics regression, multilayer perceptron, convolutional neural networks, autoencoders and denoising autoencoders, recurrent neural networks, restricted Boltzmann machines, deep belief networks, deep learning in speech and object recognition. |
|
Recom'd text(s): | Deep Learning, Ian Goodfellow, Yoshua Bengio, and Aaron Courville, The MIT Press, 2016, in preparation. Course notes will be made available. | |
Reference text(s): | --- | |
Homework(s): | Mostly writing or adapting code in Python. | |
Paper(s): | --- | |
Project(s) | --- | |
Midterm exam: | Tuesday, March 22, 2016 | |
Final Exam: | TBA | |
Grading: | Weighting: 2/5 homework, 3/10 midterm, 3/10 final | |
Hardware requirements: | Laptop for demos | |
Software requirements: | Theano and Nvidia’s Deep Neural Network Library (cuDNN) | |
Homework submission: | Mondays at noon - strict deadline. |