Deep Learning for Computer Vision
  • Home
  • Syllabus
  • Assignments And Resources
  • Instructor and TAs
  • Home
  • Syllabus
  • Assignments And Resources
  • Instructor and TAs

Syllabus and Class Schedule


DEEP LEARNING FOR COMPUTER VISION
COMS W 4995 006 (3 pts)
TR 02:40P-03:55P
Peter Belhumeur   pb2019 C002442097

Location: 451 Computer Science Building
Cap: 100
www.deeplearningforcomputervision.com

Sep 8:  Introduction to the Course (slides)
Sep 13:  Introduction to Computer Vision (slides) 
Sep 15:  Introduction to Machine Learning (slides)
Sep 20:  Probability, Bayes Theorem and Bayes Classification (slides)
Sep 22:
High-Dim Feature Spaces, Curse of Dimensionality, Gradient Descent, SVMs (slides) (jupyter notebooks)
Sep 27:  Logistic Regression, Computational Graphs, Backpropagation  (slides) 
Sep 29:  Linear Networks, Troubles with XOR,  Perceptron, Hidden Layers, MLPs (slides)
Oct 4:  More on: Linear Networks, Troubles with XOR,  Perceptron, Hidden Layers, MLPs (slides from last class)
Oct 6:  Python and Numpy Tutorial
Oct 11:  Universal Approximation Theorem, Multi-class Classification (slides)
Oct 13:  Multi-class Classification, Softmax, Regularization (slides from last class)
Oct 18:
Early Stopping, Bagging, Ensemble Methods, Dropout, Data Augmentation 
 (same slides as last class)
Oct 20: Working with Images and Convolution (slides)
Oct 25: Convolutional Neural Networks (CNNs) (same slides as last class)
Oct 27:  An Introduction to Deep Learning Frameworks and Cloud Computing (slides)
Nov 1: A Quick History of Image Datasets, Big Datasets, Deeper Deep Nets (slides)
Nov 4: Discuss Final Projects and Pizza Day
Nov 8: ELECTION DAY, NO CLASS
Nov 10: Domain Transfer, Fine-Tuning Deep Nets, and DeepNet Regressors for Object Detection/Localization (slides) 
Nov 15: Optimization (slides)
Nov 17: RNNs, LSTMs, GRUs, and Transformers (slides) 
Nov 22: NO CLASS ​
Nov 24: THANKSGIVING, NO CLASS 
Nov 29: Image Captioning (same slides as last class) 
Dec 1: Autoencoders (slides) and Generative Adversarial Networks (slides)
Dec 6: Student Presentations
Dec 8: Student Presentations 
Dec 9: Final Projects Due

Grading: Assignments = 60%   +   Final Project Proposal = 5%   +   Final Project = 35%