## Syllabus and Class Schedule

DEEP LEARNING FOR COMPUTER VISION

COMS W 4995 004 (3 pts)

TR 02:40P-03:55P

Peter Belhumeur pb2019 C002442097

Cap: 45

www.deeplearningforcomputervision.com

COMS W 4995 004 (3 pts)

TR 02:40P-03:55P

Peter Belhumeur pb2019 C002442097

Cap: 45

www.deeplearningforcomputervision.com

Jan 17: Introduction to the Course (slides)

Jan 19: Introduction to Computer Vision (slides)

Jan 24: Introduction to Machine Learning (slides)

Jan 26: Probability, Bayes Theorem and Bayes Classification (slides)

Jan 31: Introduction to Python and Numpy (jupyter notebook)

Feb 2: High-Dim Feature Spaces, Curse of Dimensionality, Gradient Descent, SVMs (slides) (jupyter notebooks)

Feb 7: Logistic Regression, Computational Graphs, Backpropagation (slides) (jupyter notebook)

Feb 9: ***Snow Day***

Feb 14: More on: Logistic Regression, Computational Graphs, Backpropagation (same slides as last class)

Feb 16: Linear Networks, Troubles with XOR, Perceptron, Hidden Layers, MLPs (slides)(jupyter notebook)

Feb 21: Universal Approximation Theorem, Multi-class Classification, Softmax (slides)

Feb 23: Regularization (same slides as last class)

Feb 28: Early Stopping, Bagging, Ensemble Methods, Dropout, Data Augmentation (same slides as last class)

Mar 2: Working with Images and Convolution (slides)

Mar 7: Convolutional Neural Networks (CNNs) (same slides as last class) (MNIST jupyter notebook) (CIFAR-10 jupyter notebook)

Mar 9: Final Project Discussions

Mar 14: Spring Break

Mar 16: Spring Break

Mar 21: A Quick History of Image Datasets, Big Datasets, Deeper Deep Nets (slides)

Mar 23: An Introduction to Deep Learning Frameworks and Cloud Computing (slides)

Mar 28: Domain Transfer, Fine-Tuning Deep Nets, and DeepNet Regressors for Object Detection/Localization (slides) (Domain Transfer jupyter notebook)

Mar 30: Optimization (slides)

Apr 4: RNNs, LSTMs, and GRUs (slides) (LSTM Character Prediction jupyter notebook)

Apr 6: ***Missed Class***

Apr 11: Image Captioning (same slides as last class)

Apr 13: Autoencoders (slides)

Apr 18: Generative Advsersarial Networks (slides)

Apr 20: Student Presentations (schedule)

Apr 25: Student Presentations (schedule)

Apr 27: Student Presentations (schedule)

Jan 19: Introduction to Computer Vision (slides)

Jan 24: Introduction to Machine Learning (slides)

Jan 26: Probability, Bayes Theorem and Bayes Classification (slides)

Jan 31: Introduction to Python and Numpy (jupyter notebook)

Feb 2: High-Dim Feature Spaces, Curse of Dimensionality, Gradient Descent, SVMs (slides) (jupyter notebooks)

Feb 7: Logistic Regression, Computational Graphs, Backpropagation (slides) (jupyter notebook)

Feb 9: ***Snow Day***

Feb 14: More on: Logistic Regression, Computational Graphs, Backpropagation (same slides as last class)

Feb 16: Linear Networks, Troubles with XOR, Perceptron, Hidden Layers, MLPs (slides)(jupyter notebook)

Feb 21: Universal Approximation Theorem, Multi-class Classification, Softmax (slides)

Feb 23: Regularization (same slides as last class)

Feb 28: Early Stopping, Bagging, Ensemble Methods, Dropout, Data Augmentation (same slides as last class)

Mar 2: Working with Images and Convolution (slides)

Mar 7: Convolutional Neural Networks (CNNs) (same slides as last class) (MNIST jupyter notebook) (CIFAR-10 jupyter notebook)

Mar 9: Final Project Discussions

Mar 14: Spring Break

Mar 16: Spring Break

Mar 21: A Quick History of Image Datasets, Big Datasets, Deeper Deep Nets (slides)

Mar 23: An Introduction to Deep Learning Frameworks and Cloud Computing (slides)

Mar 28: Domain Transfer, Fine-Tuning Deep Nets, and DeepNet Regressors for Object Detection/Localization (slides) (Domain Transfer jupyter notebook)

Mar 30: Optimization (slides)

Apr 4: RNNs, LSTMs, and GRUs (slides) (LSTM Character Prediction jupyter notebook)

Apr 6: ***Missed Class***

Apr 11: Image Captioning (same slides as last class)

Apr 13: Autoencoders (slides)

Apr 18: Generative Advsersarial Networks (slides)

Apr 20: Student Presentations (schedule)

Apr 25: Student Presentations (schedule)

Apr 27: Student Presentations (schedule)

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