Course Schedule#

Last updated May 31, 2023

Week 1 - 4/4, 4/6#

Lectures

Lecture 1: Logistics, Introduction to course, goals, biological data types, conceptual overview of deep learning and terminology (e.g. what are features, representations, tasks, etc.)

Lecture 2: Images as data, Sequences as data. Image augmentation with affine transformations. Representing sequences as one hot vectors

Recitations

Recitation 1: Cloud compute system intro. Introduction to assignment one.

Resources

Moen, E., Bannon, D., Kudo, T., Graf, W., Covert, M., & Van Valen, D. (2019). Deep learning for cellular image analysis. Nature methods, 1-14.

LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436-444.

Eraslan, G., Avsec, Z., Gagneur, J., & Theis, F. J. (2019). Deep learning: new computational modelling techniques for genomics. Nature Reviews Genetics, 20(7), 389-403.

Week 2 - 4/11, 4/13#

Lectures

Lecture 3: Example Linear Classifier

Lecture 4: Conceptual overview of deep learning.

Resources

Gamper, J., Koohbanani, N. A., Benet, K., Khuram, A., & Rajpoot, N. (2019). PanNuke: an open pan-cancer histology dataset for nuclei instance segmentation and classification. In European Congress on Digital Pathology (pp. 11-19). Springer, Cham.

Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017). ImageNet classification with deep convolutional neural networks. Communications of the ACM, 60(6), 84-90.

Breaking Linear Classifiers on ImageNet

Week 3 - 4/18, 4/20#

Lectures

Lecture 5: Linear classifier example: stochastic gradient descent, backpropagation, regularization, overfitting, underfitting, dataset splitting. Data annotation. Types of annotations for images - points, bounding boxes, dense pixel level labeling. Annotation for sequences.

Lecture 6: Problem framing. Real world tasks: Classification, segmentation, tracking, clustering. Model tasks: Classification, regression, vector embedding. How to frame real world tasks as model tasks

Recitations

Recitation 3: Intro to attention

Resources

Van Valen, D.A. et al. (2016). Deep Learning Automates the Quantitative Analysis of Individual Cells in Live-Cell Imaging Experiments. PLOS Computational Biology 12, e1005177.

Ronneberger, O., Fischer, P., & Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer-assisted intervention (pp. 234-241). Springer, Cham.

Week 4 - 4/25, 4/27#

Lectures

Lecture 7: Loss functions and optimizers. Classification - cross entropies, class imbalance, weighted cross entropy, focal loss. Regression - MSE. Optimizers - SGD, Momentum, RMSprop, Adam, Adam variants.

Lecture 8: Vision models. Model components - convolutions, pooling, activations, batch normalization. Initialization of weights. Components -> Layers. Model elements dealing with multiple spatial scales (U-Nets and FPNs). Themes in modern architectures - ResNets, DenseNets, Neural Architecture Search. Attention.

Recitations

Recitation 4: Project discussions

Notebooks

Resources

Simon Prince, Understanding Deep Learning (Chapter 5)

Jay Alammar, The Illustrated Transformer

Vaswani, Ashish, et al. (2017) Attention is all you need. In Advances in neural information processing systems 30.

Bai, M., & Urtasun, R. (2017). Deep watershed transform for instance segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 5221-5229).

Week 5 - 5/2, 5/4#

Lectures

Lecture 9: Guest Lecture by Kevin Yang (Microsoft Research)

Lecture 10: No lecture

Recitations

Recitation 5: Project discussions

Resources

Wu, K. E., Yang, K. K., Berg, R. V. D., Zou, J. Y., Lu, A. X., & Amini, A. P. (2022). Protein structure generation via folding diffusion. arXiv preprint arXiv:2209.15611.

He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770-778).

Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017). Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 4700-4708).

Lin, T. Y., Dollár, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017). Feature pyramid networks for object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2117-2125).

Week 6 - 5/9, 5/11#

Assignment

assignments/assignment-4

Lectures

Lecture 11: Example: character level language modeling using MLP.

Lecture 12: Guest Lecture by Ross Barnowski

Recitations

Recitation 6: Project discussions

Resources

Ash, J.T., Darnell, G., Munro, D., and Engelhardt, B.E. (2021). Joint analysis of expression levels and histological images identifies genes associated with tissue morphology. Nature Communications 12, 1609.

Rives, A. et al. (2021). Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences. Proc Natl Acad Sci USA 118, e2016239118.

Makemore series

Week 7 - 5/16, 5/18#

Lectures

Lecture 13: Tips and tricks I. Problem framing, data collection and curation, what architecture to choose, what loss function to choose, blending deep learning with existing methods.

Lecture 14: Tips and tricks II: How to debug when things go wrong. Follow the data schema for debugging deep learning workflows. Common errors and their fixes.

Recitations

Recitation 7: No recitation

Week 8 - 5/23, 5/25#

Lectures

Lecture 15: Guest lecture by Sam Cooper (Phenomic AI)

Lecture 16: Guest lecture by Gabriele Corso (MIT)

Recitations

Recitation 8: Intro to generative modeling: VAEs

Resources

Corso, G., Stärk, H., Jing, B., Barzilay, R., & Jaakkola, T. (2022). Diffdock: Diffusion steps, twists, and turns for molecular docking. arXiv preprint arXiv:2210.01776.

Karpathy, A. (2019). A Recipe for Training Neural Networks.

Week 9 - 5/30, 6/1#

Lectures

Lecture 17: Guest lecture by Brian Hie (Stanford/Meta)

Lecture 18: Project discussions

Recitations

Recitation 9: Basic VAE

Resources

Hsu, C., Verkuil, R., Liu, J., Lin, Z., Hie, B., Sercu, T., … & Rives, A. (2022, June). Learning inverse folding from millions of predicted structures. In International Conference on Machine Learning (pp. 8946-8970). PMLR.

Hie, B., Zhong, E. D., Berger, B., & Bryson, B. (2021). Learning the language of viral evolution and escape. Science, 371(6526), 284-288.

Week 10 - 6/6, 6/8#

Lectures

No lectures.