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 004 (3 pts)
TR 02:40P-03:55P
Peter Belhumeur   pb2019 C002442097

Location: 413 Kent Hall
Cap: 60
www.deeplearningforcomputervision.com

Sep 9:  Introduction to the Course (slides)
Sep 14:  Introduction to Computer Vision (slides) 
Sep 16:  Introduction to Machine Learning (slides)
Sep 21:  Probability, Bayes Theorem and Bayes Classification (slides)
Sep 23: Introduction to Python and Numpy (jupyter notebook)
Sep 28:  High-Dim Feature Spaces, Curse of Dimensionality, Gradient Descent, SVMs (slides) (jupyter notebooks)
Sep 30:  Logistic Regression, Computational Graphs, Backpropagation  (slides) 
Oct 5:  More on: 
Logistic Regression, Computational Graphs, Backpropagation (same slides as last class)
Oct 7:  Linear Networks, Troubles with XOR,  Perceptron, Hidden Layers, MLPs (slides)
Oct 12:  More on...Linear Networks, Troubles with XOR,  Perceptron, Hidden Layers, MLPs (slides)
Oct 14:  Universal Approximation Theorem, Multi-class Classification, Softmax (slides)
Oct 19: Regularization (same slides as last class)
Oct 21: Early Stopping, Bagging, Ensemble Methods, Dropout, Data Augmentation 
 (same slides as last class)
Oct 26:  Working with Images and Convolution (slides)
Oct 28:  Convolutional Neural Networks (CNNs) (same slides as last class)
Nov 2: NO CLASS
Nov 4: A Quick History of Image Datasets, Big Datasets, Deeper Deep Nets (slides)
Nov 9: An Introduction to Deep Learning Frameworks and Cloud Computing (slides)
Nov 11: Domain Transfer, Fine-Tuning Deep Nets, and DeepNet Regressors for Object Detection/Localization (slides) 
Nov 16: Optimization (slides)
Nov 18: RNNs, LSTMs, GRUs, and Transformers (slides) 
Nov 23: Discuss Final Projects and Pizza Day
Nov 25: 
NO CLASS
Nov 30: Image Captioning (same slides as last class) 
Dec 2: Autoencoders (slides) and Generative Advsersarial Networks (slides)
Dec 7: Student Presentations
Dec 9: Student Presentations 
Dec 14: Final Projects Due

Grading: Assignments = 60%   +   Final Project Proposal = 5%   +   Final Project = 35%
Powered by Create your own unique website with customizable templates.