Deep Learning – Spring 2017
We are going to take “get your hands dirty” approach, you will be given assignments and projects to implement ideas discussed in the class. Projects and assignments will contain miniature versions of real life existing applications and problems (e.g can you train your computer to generate dialogues in Shakespeare style or convert your image into painting as done by Monet, sentiment analysis etc.. ).
Course will concentrate in developing both mathematical knowledge and implementation capabilities. We will start from training a single perceptron, move to training a deep neural network, study why training large networks is a problem and what could be its possible solutions. After dipping our toes in deep belief networks and recurrent neural network we will start looking into applications of deep learning in three different areas, text-analysis, speech processing and computer vision. Objective of this approach is to make you comfortable enough that you can understand various research problems and, if interested, can implement deep learning based applications.
In last few years machine learning has matured from the science fiction to reality. We are living in a world where we have already seen industry bringing to reality self-driving cars, face-recognizers that work on massive scale (facebook), speech translation systems that can translate from one language to many other simultaneously and in real-time, and more interestingly we have machines that can learn to play atari games in a similar fashion like we do.
A lot of these victories have come from the exciting field of Deep Learning; a learning methodology based on the concept that human mind captures details at multiple levels or at multiple abstract levels. One property of deep learning is removing the responsibility of humans to design features, instead Deep Learning is given a task to find the appropriate representation.
Office Hours and Contact Info.
Instructor: Dr. Mohsen Ali
2:00 pm to 4:00 pm Tuesday & Thursday (or by appointment)
Teaching Assistant: : Ali Hassan (TA Hours: Fridays 9:30 am — 11:30am)
Teaching Assistant: : Afsheen Rafaqat Ali (volunteer)
Probability, linear algebra, programming ability and desire to read & implement.
- 50% Assignments
- 15% Final Project
- 10% Quizzes
- 10% Midterm Exam
- 15% Final Exam
All cases of academic misconduct will be forwarded to the disciplinary committee. All assignments are individual unless explicitly specified by the instructor. In the words of Efros, let’s not embarrass ourselves.
|Feb 2, 2017||Introduction to Deep Learning|
|Feb 3, 2017||Linear Regression Least Squares Estimation|
|Feb 7, 2017||Linear Classifier Perceptron Rule Sigmoid Perceptron Reading:|
|Feb 9, 2017||Logistic Regression Concepts of local minima, local maxima, convex functions, concave functions, critical points Error Function of Linear Regression and convexity A simple code for the Perceptron|
|Feb 14, 2017||Gradient descent:|
|Feb 16, 2017||Back Propagation-1 Reading:|
|Feb 21, 2017||Back Propagation-2|
|Feb 28, 2017||How to Train Neural Network Reading:|
|Mar 2, 2017||Representational or Expressive Power of Deep Neural Network (Section 6.4 Deep Learing, by Good Fellow, Bengio & Courville) Universal Approximation Properties of Single Layer Neural Network Problems in training, generalization and efficiency Does increasing depth always results in much better generalization?|
|Mar 7, 2017||Convolutional Neural Networks Video Lecture :
|Mar 9, 2017||CNN, Regularizations and Updation RulesReading: Things to Take Care of While implementing DNN|
|Mar 14, 2017||Network Visualization|
|Apr 4, 2017||Object Localization and Detection Regression for the localization Concept of object proposals RCNN/Fast-RCNN/Faster-RCNN YOLO|
|Apr 6, 2017||Object Localization Reading & Resources|
|Apr 11, 2017||RNN LSTM Image Caption Generation using LSTM|
|Apr 13, 2017||Image Segmentation Architectures Concepts of Dropout, connect it to visualization|
|Apr 18, 2017||Presentation on LipNet: End-to-End Sentence-level Lipreading Presented by Sanullah Manzoor PhdCS-16003|
|Apr 20, 2017||Slides Hugo Larochelle’s lectures are treat|
|Apr 25, 2017||Generative Adversarial Networks Paper An introduction to Generative Adversarial Networks (with code in TensorFlow) Introductory guide to Generative Adversarial Networks (GANs) and their promise!|
|Apr 27, 2017||Understanding different architectures used for the Video Analysis|
Papers Presented by Students
- Accurate Image Super-Resolution Using Very Deep Convolutional Networks – CVPR 2016
- DeepFashion: Powering Robust Clothes Recognition and Retrieval with Rich Annotations – CVPR 2016
- End to End Learning for Self-Driving Cars – CVPR 2016
- Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models
- Domain Adaptation for Large-Scale Sentiment Classification: A Deep Learning Approach – ICML 2011
- Lip Reading Sentences in the Wild – CVPR 2017
- Harnessing Object and Scene Semantics for Large-Scale Video Understanding – CVPR 2016
- Mask R-CNN – CVPR 2016
- Short Text Clustering via Convolutional Neural Networks – NAACL-HLT. 2015
- Recurrent Convolutional Neural Networks for Text Classification – AAAI 2015
- Neural responding machine for short-text conversation – arXiv 2015
- LipNet: Sentence-level Lipreading – arXiv 2016
- A persona-based neural conversation model – arXiv
- Sequence to sequence learning with neural networks – NIPS 2014
- A machine learning approach to visual perception of forest trails for mobile robots – IEEE Robotics and Automation Letters 1.2 2016