Syllabus and Class Schedule
DEEP LEARNING FOR COMPUTER VISION
COMS W 4995 011 (3 pts)
TR 02:40P-03:55P
Peter Belhumeur pb2019 C002442097
Location: 428 Pupin
Cap: 100
www.deeplearningforcomputervision.com
COMS W 4995 011 (3 pts)
TR 02:40P-03:55P
Peter Belhumeur pb2019 C002442097
Location: 428 Pupin
Cap: 100
www.deeplearningforcomputervision.com
Sep 5: Introduction to the Course (slides)
Sep 7: Introduction to Computer Vision (slides)
Sep 12: Introduction to Machine Learning (slides)
Sep 14: Probability, Bayes Theorem and Bayes Classification (slides)
Sep 19: High-Dim Feature Spaces, Curse of Dimensionality, Gradient Descent, SVMs (slides) (jupyter notebook)
Sep 21: Logistic Regression, Computational Graphs, Backpropagation (slides)
Sep 26: Linear Networks, Troubles with XOR, Perceptron, Hidden Layers, MLPs (slides)
Sep 28: More on: Linear Networks, Troubles with XOR, Perceptron, Hidden Layers, MLPs (slides from last class)
Oct 3: Python and Numpy Tutorial
Oct 5: Universal Approximation Theorem, Multi-class Classification (slides)
Oct 10: Multi-class Classification, Softmax, Regularization (slides from last class)
Oct 12: Early Stopping, Bagging, Ensemble Methods, Dropout, Data Augmentation (same slides as last class)
Oct 17: Working with Images and Convolution (slides)
Oct 19: Convolutional Neural Networks (CNNs) (same slides as last class)
Oct 24: NO CLASS
Oct 26: A Quick History of Image Datasets, Big Datasets, Deeper Deep Nets (slides)
Oct 31: An Introduction to Deep Learning Frameworks and Cloud Computing (slides)
Nov 2: Discuss Final Projects and Pizza Day
Nov 7: ELECTION DAY, NO CLASS
Nov 9: Domain Transfer, Fine-Tuning Deep Nets, and DeepNet Regressors for Object Detection/Localization (slides)
Nov 14: Optimization (slides)
Nov 16: RNNs, LSTMs, GRUs, and Transformers (slides)
Nov 21: NO CLASS
Nov 23: THANKSGIVING, NO CLASS
Nov 28: Image Captioning (same slides as last class)
Nov 30: Transformer and LLMs in Detail (slides)
Dec 5: Student Presentations
Dec 7: Student Presentations
Dec 8: Final Projects Due
Grading: Assignments = 60% + Final Project Proposal = 5% + Final Project = 35%
Sep 7: Introduction to Computer Vision (slides)
Sep 12: Introduction to Machine Learning (slides)
Sep 14: Probability, Bayes Theorem and Bayes Classification (slides)
Sep 19: High-Dim Feature Spaces, Curse of Dimensionality, Gradient Descent, SVMs (slides) (jupyter notebook)
Sep 21: Logistic Regression, Computational Graphs, Backpropagation (slides)
Sep 26: Linear Networks, Troubles with XOR, Perceptron, Hidden Layers, MLPs (slides)
Sep 28: More on: Linear Networks, Troubles with XOR, Perceptron, Hidden Layers, MLPs (slides from last class)
Oct 3: Python and Numpy Tutorial
Oct 5: Universal Approximation Theorem, Multi-class Classification (slides)
Oct 10: Multi-class Classification, Softmax, Regularization (slides from last class)
Oct 12: Early Stopping, Bagging, Ensemble Methods, Dropout, Data Augmentation (same slides as last class)
Oct 17: Working with Images and Convolution (slides)
Oct 19: Convolutional Neural Networks (CNNs) (same slides as last class)
Oct 24: NO CLASS
Oct 26: A Quick History of Image Datasets, Big Datasets, Deeper Deep Nets (slides)
Oct 31: An Introduction to Deep Learning Frameworks and Cloud Computing (slides)
Nov 2: Discuss Final Projects and Pizza Day
Nov 7: ELECTION DAY, NO CLASS
Nov 9: Domain Transfer, Fine-Tuning Deep Nets, and DeepNet Regressors for Object Detection/Localization (slides)
Nov 14: Optimization (slides)
Nov 16: RNNs, LSTMs, GRUs, and Transformers (slides)
Nov 21: NO CLASS
Nov 23: THANKSGIVING, NO CLASS
Nov 28: Image Captioning (same slides as last class)
Nov 30: Transformer and LLMs in Detail (slides)
Dec 5: Student Presentations
Dec 7: Student Presentations
Dec 8: Final Projects Due
Grading: Assignments = 60% + Final Project Proposal = 5% + Final Project = 35%