Learning and Perception - Fall 2020- 896874

Staff:

Prof Gal Chechik (webpage)
Dvir Samuel (webpage)
Ran Algiser (webpage)
For questions, email biu.cs.896874@gmail.com.

Time and place:

Place: Link to Zoom by invitation only for registered students
Time: Mondays 2PM -- 4PM

Administration:

There are 5 home assignments in the course, and one final project. The home assignments will be a mix of questions and programming assignments.
Home assignments can be done in pairs, or individually
The submission date for the final project will be Feb 28th 2021. The final grade is based on 30 percent final project, and 70 percent home assignments
See the syllabus .

Home assignment:

TopicLinkSubmission dateSolutionGrades
Ex 1: Linear classification, Pytorch colab, data Sun 2020-11-08 Solution Grades on Moodle
Ex 2: Convolutional deep networks, multi-class colab, data Sun 2020-11-22 Solution Grades on Moodle
Ex 3: Object detection colab Sun 2020-12-13 Solution Grades on Moodle
Ex 4: Style transfer, GradCAM colab Sun 2020-12-30 Solution Grades on Moodle
Ex 5:Self Supervised learning, GANs colab Sun 2020-01-20 Solution Grades on Moodle
Proposals for the final project Instructions Sun 2021-01-15 (can be extended to Jan 31st)

List of classes:

DateTopicZoom recordingonline material
2020-10-19 Introduction to machine learning: Generalization, Polynomial regression Recording PRML , Slides
2020-10-26 Linear classifiers, Optimiztion with SGD Recording Slides
2020-11-02 Deep networks, multi-class classification softmax Recording Slides
2020-11-09 MLPs, ConvNets Recording Slides
2020-11-16 Modern architectures, Batch Norm, Augmentation Recording Slides
2020-11-23 ResNets, Optimization Recording Slides
2020-11-30 Object detection Recording Slides
2020-12-07 Workflows, Self supervised learning Recording XENT , Workflows , SSL 1
2020-12-14 SSL, Contrastive SSL 2 SSL 2
2020-12-21 Visualization, Style Transfer Recording Slides
2020-12-28 Generative approaches GAN Recording Slides (permission fixed now)
2021-01-04 Generative approaches VAEs Recording Slides
2021-01-11 Vision and language Recording Slides
2021-01-18 No class - -

Related material (books)

Pattern Recognition and Machine Learning , Chris Bishop
Deep Learning Ian Goodfellow and Yoshua Bengio and Aaron Courville, MIT Press, 2016.
Understanding Machine Learning: From Theory to Algorithms Shai Shalev-Shwartz and Shai Ben-David.

Related online courses

For self-supervised learning, VAEs and GANs: Berkeley CS294 Peter Abbeel.
For computer vision using deep learning : Stanford CS231 Fei-Fei Li.
For deep learning: Dive into DL Alex Smola.