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 001 (3 pts)
TR 02:40P-03:55P
Peter Belhumeur   pb2019 C002442097

Location: 402 Chandler
Cap: 125
www.deeplearningforcomputervision.com

Sep 2:  Introduction to the Course (slides)
Sep 4:  Introduction to Computer Vision (slides) 
Sep 9:  Introduction to Machine Learning (slides)
Sep 11:  Probability, Bayes Theorem and Bayes Classification (slides)
Sep 16:
High-Dim Feature Spaces, Curse of Dimensionality, Gradient Descent, SVMs (slides) (jupyter notebook)
Sep 18:  Logistic Regression, Computational Graphs, Backpropagation  (slides) 
Sep 23:  Linear Networks, Troubles with XOR,  Perceptron, Hidden Layers, MLPs (slides)
Sep 25:  More on: Linear Networks, Troubles with XOR,  Perceptron, Hidden Layers, MLPs (slides from last class)
Sep 30:  Python and Numpy Tutorial
Oct 2:  Universal Approximation Theorem, Multi-class Classification (slides)
Oct 7:  Multi-class Classification, Softmax, Regularization (slides from last class)
Oct 9: Early Stopping, Bagging, Ensemble Methods, Dropout, Data Augmentation  (same slides as last class)
Oct 14: Working with Images and Convolution (slides)
Oct 16: Convolutional Neural Networks (CNNs) (same slides as last class)
Oct 21: A Quick History of Image Datasets, Big Datasets, Deeper Deep Nets (slides)
Oct 23: Python, Jupyter Notebooks, Cloud Computing Tutorial
Oct 28:  An Introduction to Deep Learning Frameworks and Cloud Computing (slides)
Oct 30: Discuss Final Projects and Pizza Day
Nov 4: ELECTION DAY, NO CLASS
Nov 6: Domain Transfer, Fine-Tuning Deep Nets, and DeepNet Regressors for Object Detection/Localization (slides) 
Nov 11: Optimization (slides)
Nov 13: RNNs, LSTMs, GRUs, and Transformers (slides) 
Nov 18: Image Captioning (same slides as last class)  
Nov 20: Transformer and LLMs in Detail (slides) ​
Nov 25: NO CLASS, THANKSGIVING BREAK 
Nov 27: NO CLASS, THANKSGIVING BREAK 
Dec 2: Student Presentations
Dec 4: Student Presentations
Dec 8: Final Projects Due

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